[compat, networking] Deprecate old functions (#2861)

Authored by: coletdjnz, pukkandan
This commit is contained in:
coletdjnz 2023-07-09 13:23:02 +05:30 committed by pukkandan
parent 227bf1a33b
commit 3d2623a898
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
176 changed files with 707 additions and 729 deletions

View File

@ -160,7 +160,7 @@ def generator(test_case, tname):
force_generic_extractor=params.get('force_generic_extractor', False)) force_generic_extractor=params.get('force_generic_extractor', False))
except (DownloadError, ExtractorError) as err: except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one # Check if the exception is not a network related one
if not isinstance(err.exc_info[1], (TransportError, UnavailableVideoError)) or (isinstance(err.exc_info[1], HTTPError) and err.exc_info[1].code == 503): if not isinstance(err.exc_info[1], (TransportError, UnavailableVideoError)) or (isinstance(err.exc_info[1], HTTPError) and err.exc_info[1].status == 503):
err.msg = f'{getattr(err, "msg", err)} ({tname})' err.msg = f'{getattr(err, "msg", err)} ({tname})'
raise raise

View File

@ -1057,14 +1057,15 @@ class TestYoutubeDLNetworking:
urllib_req = urllib.request.Request('http://foo.bar', data=b'test', method='PUT', headers={'X-Test': '1'}) urllib_req = urllib.request.Request('http://foo.bar', data=b'test', method='PUT', headers={'X-Test': '1'})
urllib_req.add_unredirected_header('Cookie', 'bob=bob') urllib_req.add_unredirected_header('Cookie', 'bob=bob')
urllib_req.timeout = 2 urllib_req.timeout = 2
with warnings.catch_warnings():
req = ydl.urlopen(urllib_req).request warnings.simplefilter('ignore', category=DeprecationWarning)
assert req.url == urllib_req.get_full_url() req = ydl.urlopen(urllib_req).request
assert req.data == urllib_req.data assert req.url == urllib_req.get_full_url()
assert req.method == urllib_req.get_method() assert req.data == urllib_req.data
assert 'X-Test' in req.headers assert req.method == urllib_req.get_method()
assert 'Cookie' in req.headers assert 'X-Test' in req.headers
assert req.extensions.get('timeout') == 2 assert 'Cookie' in req.headers
assert req.extensions.get('timeout') == 2
with pytest.raises(AssertionError): with pytest.raises(AssertionError):
ydl.urlopen(None) ydl.urlopen(None)
@ -1362,7 +1363,9 @@ class TestResponse:
def test_compat(self): def test_compat(self):
res = Response(io.BytesIO(b''), url='test://', status=404, headers={'test': 'test'}) res = Response(io.BytesIO(b''), url='test://', status=404, headers={'test': 'test'})
assert res.code == res.getcode() == res.status with warnings.catch_warnings():
assert res.geturl() == res.url warnings.simplefilter('ignore', category=DeprecationWarning)
assert res.info() is res.headers assert res.code == res.getcode() == res.status
assert res.getheader('test') == res.get_header('test') assert res.geturl() == res.url
assert res.info() is res.headers
assert res.getheader('test') == res.get_header('test')

View File

@ -8,11 +8,13 @@ import pytest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import contextlib
import io import io
import platform import platform
import random import random
import ssl import ssl
import urllib.error import urllib.error
import warnings
from yt_dlp.cookies import YoutubeDLCookieJar from yt_dlp.cookies import YoutubeDLCookieJar
from yt_dlp.dependencies import certifi from yt_dlp.dependencies import certifi
@ -202,20 +204,58 @@ class TestNetworkingExceptions:
assert isinstance(error, HTTPError) assert isinstance(error, HTTPError)
assert isinstance(error, urllib.error.HTTPError) assert isinstance(error, urllib.error.HTTPError)
assert error.code == 403 @contextlib.contextmanager
assert error.getcode() == 403 def raises_deprecation_warning():
assert error.hdrs is error.response.headers with warnings.catch_warnings(record=True) as w:
assert error.info() is error.response.headers warnings.simplefilter('always')
assert error.headers is error.response.headers yield
assert error.filename == error.response.url
assert error.url == error.response.url if len(w) == 0:
assert error.geturl() == error.response.url pytest.fail('Did not raise DeprecationWarning')
if len(w) > 1:
pytest.fail(f'Raised multiple warnings: {w}')
if not issubclass(w[-1].category, DeprecationWarning):
pytest.fail(f'Expected DeprecationWarning, got {w[-1].category}')
w.clear()
with raises_deprecation_warning():
assert error.code == 403
with raises_deprecation_warning():
assert error.getcode() == 403
with raises_deprecation_warning():
assert error.hdrs is error.response.headers
with raises_deprecation_warning():
assert error.info() is error.response.headers
with raises_deprecation_warning():
assert error.headers is error.response.headers
with raises_deprecation_warning():
assert error.filename == error.response.url
with raises_deprecation_warning():
assert error.url == error.response.url
with raises_deprecation_warning():
assert error.geturl() == error.response.url
# Passthrough file operations # Passthrough file operations
assert error.read() == b'test' with raises_deprecation_warning():
assert not error.closed assert error.read() == b'test'
# Technically Response operations are also passed through, which should not be used.
assert error.get_header('test') == 'test' with raises_deprecation_warning():
assert not error.closed
with raises_deprecation_warning():
# Technically Response operations are also passed through, which should not be used.
assert error.get_header('test') == 'test'
# Should not raise a warning
error.close()
@pytest.mark.skipif( @pytest.mark.skipif(
platform.python_implementation() == 'PyPy', reason='garbage collector works differently in pypy') platform.python_implementation() == 'PyPy', reason='garbage collector works differently in pypy')

View File

@ -33,7 +33,7 @@ from .extractor import gen_extractor_classes, get_info_extractor
from .extractor.common import UnsupportedURLIE from .extractor.common import UnsupportedURLIE
from .extractor.openload import PhantomJSwrapper from .extractor.openload import PhantomJSwrapper
from .minicurses import format_text from .minicurses import format_text
from .networking import Request, RequestDirector from .networking import HEADRequest, Request, RequestDirector
from .networking.common import _REQUEST_HANDLERS from .networking.common import _REQUEST_HANDLERS
from .networking.exceptions import ( from .networking.exceptions import (
HTTPError, HTTPError,
@ -41,6 +41,7 @@ from .networking.exceptions import (
RequestError, RequestError,
SSLError, SSLError,
_CompatHTTPError, _CompatHTTPError,
network_exceptions,
) )
from .plugins import directories as plugin_directories from .plugins import directories as plugin_directories
from .postprocessor import _PLUGIN_CLASSES as plugin_pps from .postprocessor import _PLUGIN_CLASSES as plugin_pps
@ -80,7 +81,6 @@ from .utils import (
ExtractorError, ExtractorError,
FormatSorter, FormatSorter,
GeoRestrictedError, GeoRestrictedError,
HEADRequest,
ISO3166Utils, ISO3166Utils,
LazyList, LazyList,
MaxDownloadsReached, MaxDownloadsReached,
@ -122,7 +122,6 @@ from .utils import (
locked_file, locked_file,
make_archive_id, make_archive_id,
make_dir, make_dir,
network_exceptions,
number_of_digits, number_of_digits,
orderedSet, orderedSet,
orderedSet_from_options, orderedSet_from_options,
@ -135,7 +134,6 @@ from .utils import (
sanitize_filename, sanitize_filename,
sanitize_path, sanitize_path,
sanitize_url, sanitize_url,
std_headers,
str_or_none, str_or_none,
strftime_or_none, strftime_or_none,
subtitles_filename, subtitles_filename,
@ -158,6 +156,7 @@ from .utils.networking import (
HTTPHeaderDict, HTTPHeaderDict,
clean_headers, clean_headers,
clean_proxies, clean_proxies,
std_headers,
) )
from .version import CHANNEL, RELEASE_GIT_HEAD, VARIANT, __version__ from .version import CHANNEL, RELEASE_GIT_HEAD, VARIANT, __version__
@ -4019,6 +4018,9 @@ class YoutubeDL:
if isinstance(req, str): if isinstance(req, str):
req = Request(req) req = Request(req)
elif isinstance(req, urllib.request.Request): elif isinstance(req, urllib.request.Request):
self.deprecation_warning(
'Passing a urllib.request.Request object to YoutubeDL.urlopen() is deprecated. '
'Use yt_dlp.networking.common.Request instead.')
req = urllib_req_to_req(req) req = urllib_req_to_req(req)
assert isinstance(req, Request) assert isinstance(req, Request)
@ -4242,7 +4244,7 @@ class YoutubeDL:
ret.append((thumb_filename, thumb_filename_final)) ret.append((thumb_filename, thumb_filename_final))
t['filepath'] = thumb_filename t['filepath'] = thumb_filename
except network_exceptions as err: except network_exceptions as err:
if isinstance(err, urllib.error.HTTPError) and err.code == 404: if isinstance(err, HTTPError) and err.status == 404:
self.to_screen(f'[info] {thumb_display_id.title()} does not exist') self.to_screen(f'[info] {thumb_display_id.title()} does not exist')
else: else:
self.report_warning(f'Unable to download {thumb_display_id}: {err}') self.report_warning(f'Unable to download {thumb_display_id}: {err}')

View File

@ -57,11 +57,11 @@ from .utils import (
read_stdin, read_stdin,
render_table, render_table,
setproctitle, setproctitle,
std_headers,
traverse_obj, traverse_obj,
variadic, variadic,
write_string, write_string,
) )
from .utils.networking import std_headers
from .YoutubeDL import YoutubeDL from .YoutubeDL import YoutubeDL
_IN_CLI = False _IN_CLI = False

View File

@ -8,7 +8,6 @@ compat_str = str
compat_b64decode = base64.b64decode compat_b64decode = base64.b64decode
compat_HTTPError = urllib.error.HTTPError
compat_urlparse = urllib.parse compat_urlparse = urllib.parse
compat_parse_qs = urllib.parse.parse_qs compat_parse_qs = urllib.parse.parse_qs
compat_urllib_parse_unquote = urllib.parse.unquote compat_urllib_parse_unquote = urllib.parse.unquote

View File

@ -70,6 +70,7 @@ compat_html_parser_HTMLParseError = compat_HTMLParseError
compat_HTMLParser = compat_html_parser_HTMLParser = html.parser.HTMLParser compat_HTMLParser = compat_html_parser_HTMLParser = html.parser.HTMLParser
compat_http_client = http.client compat_http_client = http.client
compat_http_server = http.server compat_http_server = http.server
compat_HTTPError = urllib.error.HTTPError
compat_input = input compat_input = input
compat_integer_types = (int, ) compat_integer_types = (int, )
compat_itertools_count = itertools.count compat_itertools_count = itertools.count

View File

@ -10,6 +10,7 @@ import uuid
from .fragment import FragmentFD from .fragment import FragmentFD
from ..compat import functools from ..compat import functools
from ..networking import Request
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import ( from ..utils import (
Popen, Popen,
@ -25,7 +26,6 @@ from ..utils import (
encodeFilename, encodeFilename,
find_available_port, find_available_port,
remove_end, remove_end,
sanitized_Request,
traverse_obj, traverse_obj,
) )
@ -357,13 +357,12 @@ class Aria2cFD(ExternalFD):
'method': method, 'method': method,
'params': [f'token:{rpc_secret}', *params], 'params': [f'token:{rpc_secret}', *params],
}).encode('utf-8') }).encode('utf-8')
request = sanitized_Request( request = Request(
f'http://localhost:{rpc_port}/jsonrpc', f'http://localhost:{rpc_port}/jsonrpc',
data=d, headers={ data=d, headers={
'Content-Type': 'application/json', 'Content-Type': 'application/json',
'Content-Length': f'{len(d)}', 'Content-Length': f'{len(d)}',
'Ytdl-request-proxy': '__noproxy__', }, proxies={'all': None})
})
with self.ydl.urlopen(request) as r: with self.ydl.urlopen(request) as r:
resp = json.load(r) resp = json.load(r)
assert resp.get('id') == sanitycheck, 'Something went wrong with RPC server' assert resp.get('id') == sanitycheck, 'Something went wrong with RPC server'

View File

@ -3,11 +3,11 @@ import io
import itertools import itertools
import struct import struct
import time import time
import urllib.error
import urllib.parse import urllib.parse
from .fragment import FragmentFD from .fragment import FragmentFD
from ..compat import compat_etree_fromstring from ..compat import compat_etree_fromstring
from ..networking.exceptions import HTTPError
from ..utils import fix_xml_ampersands, xpath_text from ..utils import fix_xml_ampersands, xpath_text
@ -312,7 +312,7 @@ class F4mFD(FragmentFD):
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl() man_url = urlh.url
# Some manifests may be malformed, e.g. prosiebensat1 generated manifests # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
# (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244 # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244
# and https://github.com/ytdl-org/youtube-dl/issues/7823) # and https://github.com/ytdl-org/youtube-dl/issues/7823)
@ -407,8 +407,8 @@ class F4mFD(FragmentFD):
if box_type == b'mdat': if box_type == b'mdat':
self._append_fragment(ctx, box_data) self._append_fragment(ctx, box_data)
break break
except urllib.error.HTTPError as err: except HTTPError as err:
if live and (err.code == 404 or err.code == 410): if live and (err.status == 404 or err.status == 410):
# We didn't keep up with the live window. Continue # We didn't keep up with the live window. Continue
# with the next available fragment. # with the next available fragment.
msg = 'Fragment %d unavailable' % frag_i msg = 'Fragment %d unavailable' % frag_i

View File

@ -1,24 +1,19 @@
import concurrent.futures import concurrent.futures
import contextlib import contextlib
import http.client
import json import json
import math import math
import os import os
import struct import struct
import time import time
import urllib.error
from .common import FileDownloader from .common import FileDownloader
from .http import HttpFD from .http import HttpFD
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import compat_os_name from ..compat import compat_os_name
from ..utils import ( from ..networking import Request
DownloadError, from ..networking.exceptions import HTTPError, IncompleteRead
RetryManager, from ..utils import DownloadError, RetryManager, encodeFilename, traverse_obj
encodeFilename, from ..utils.networking import HTTPHeaderDict
sanitized_Request,
traverse_obj,
)
class HttpQuietDownloader(HttpFD): class HttpQuietDownloader(HttpFD):
@ -75,7 +70,7 @@ class FragmentFD(FileDownloader):
def _prepare_url(self, info_dict, url): def _prepare_url(self, info_dict, url):
headers = info_dict.get('http_headers') headers = info_dict.get('http_headers')
return sanitized_Request(url, None, headers) if headers else url return Request(url, None, headers) if headers else url
def _prepare_and_start_frag_download(self, ctx, info_dict): def _prepare_and_start_frag_download(self, ctx, info_dict):
self._prepare_frag_download(ctx) self._prepare_frag_download(ctx)
@ -457,7 +452,7 @@ class FragmentFD(FileDownloader):
frag_index = ctx['fragment_index'] = fragment['frag_index'] frag_index = ctx['fragment_index'] = fragment['frag_index']
ctx['last_error'] = None ctx['last_error'] = None
headers = info_dict.get('http_headers', {}).copy() headers = HTTPHeaderDict(info_dict.get('http_headers'))
byte_range = fragment.get('byte_range') byte_range = fragment.get('byte_range')
if byte_range: if byte_range:
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1) headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
@ -477,7 +472,7 @@ class FragmentFD(FileDownloader):
if not self._download_fragment( if not self._download_fragment(
ctx, fragment['url'], info_dict, headers, info_dict.get('request_data')): ctx, fragment['url'], info_dict, headers, info_dict.get('request_data')):
return return
except (urllib.error.HTTPError, http.client.IncompleteRead) as err: except (HTTPError, IncompleteRead) as err:
retry.error = err retry.error = err
continue continue
except DownloadError: # has own retry settings except DownloadError: # has own retry settings

View File

@ -75,7 +75,7 @@ class HlsFD(FragmentFD):
self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME) self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl() man_url = urlh.url
s = urlh.read().decode('utf-8', 'ignore') s = urlh.read().decode('utf-8', 'ignore')
can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None

View File

@ -1,10 +1,14 @@
import os import os
import random import random
import time import time
import urllib.error
from .common import FileDownloader from .common import FileDownloader
from ..networking.exceptions import CertificateVerifyError, TransportError from ..networking import Request
from ..networking.exceptions import (
CertificateVerifyError,
HTTPError,
TransportError,
)
from ..utils import ( from ..utils import (
ContentTooShortError, ContentTooShortError,
RetryManager, RetryManager,
@ -14,10 +18,10 @@ from ..utils import (
encodeFilename, encodeFilename,
int_or_none, int_or_none,
parse_http_range, parse_http_range,
sanitized_Request,
try_call, try_call,
write_xattr, write_xattr,
) )
from ..utils.networking import HTTPHeaderDict
class HttpFD(FileDownloader): class HttpFD(FileDownloader):
@ -36,10 +40,7 @@ class HttpFD(FileDownloader):
ctx.stream = None ctx.stream = None
# Disable compression # Disable compression
headers = {'Accept-Encoding': 'identity'} headers = HTTPHeaderDict({'Accept-Encoding': 'identity'}, info_dict.get('http_headers'))
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
is_test = self.params.get('test', False) is_test = self.params.get('test', False)
chunk_size = self._TEST_FILE_SIZE if is_test else ( chunk_size = self._TEST_FILE_SIZE if is_test else (
@ -110,10 +111,10 @@ class HttpFD(FileDownloader):
if try_call(lambda: range_end >= ctx.content_len): if try_call(lambda: range_end >= ctx.content_len):
range_end = ctx.content_len - 1 range_end = ctx.content_len - 1
request = sanitized_Request(url, request_data, headers) request = Request(url, request_data, headers)
has_range = range_start is not None has_range = range_start is not None
if has_range: if has_range:
request.add_header('Range', f'bytes={int(range_start)}-{int_or_none(range_end) or ""}') request.headers['Range'] = f'bytes={int(range_start)}-{int_or_none(range_end) or ""}'
# Establish connection # Establish connection
try: try:
ctx.data = self.ydl.urlopen(request) ctx.data = self.ydl.urlopen(request)
@ -144,17 +145,17 @@ class HttpFD(FileDownloader):
self.report_unable_to_resume() self.report_unable_to_resume()
ctx.resume_len = 0 ctx.resume_len = 0
ctx.open_mode = 'wb' ctx.open_mode = 'wb'
ctx.data_len = ctx.content_len = int_or_none(ctx.data.info().get('Content-length', None)) ctx.data_len = ctx.content_len = int_or_none(ctx.data.headers.get('Content-length', None))
except urllib.error.HTTPError as err: except HTTPError as err:
if err.code == 416: if err.status == 416:
# Unable to resume (requested range not satisfiable) # Unable to resume (requested range not satisfiable)
try: try:
# Open the connection again without the range header # Open the connection again without the range header
ctx.data = self.ydl.urlopen( ctx.data = self.ydl.urlopen(
sanitized_Request(url, request_data, headers)) Request(url, request_data, headers))
content_length = ctx.data.info()['Content-Length'] content_length = ctx.data.headers['Content-Length']
except urllib.error.HTTPError as err: except HTTPError as err:
if err.code < 500 or err.code >= 600: if err.status < 500 or err.status >= 600:
raise raise
else: else:
# Examine the reported length # Examine the reported length
@ -182,7 +183,7 @@ class HttpFD(FileDownloader):
ctx.resume_len = 0 ctx.resume_len = 0
ctx.open_mode = 'wb' ctx.open_mode = 'wb'
return return
elif err.code < 500 or err.code >= 600: elif err.status < 500 or err.status >= 600:
# Unexpected HTTP error # Unexpected HTTP error
raise raise
raise RetryDownload(err) raise RetryDownload(err)
@ -198,9 +199,9 @@ class HttpFD(FileDownloader):
ctx.stream = None ctx.stream = None
def download(): def download():
data_len = ctx.data.info().get('Content-length') data_len = ctx.data.headers.get('Content-length')
if ctx.data.info().get('Content-encoding'): if ctx.data.headers.get('Content-encoding'):
# Content-encoding is present, Content-length is not reliable anymore as we are # Content-encoding is present, Content-length is not reliable anymore as we are
# doing auto decompression. (See: https://github.com/yt-dlp/yt-dlp/pull/6176) # doing auto decompression. (See: https://github.com/yt-dlp/yt-dlp/pull/6176)
data_len = None data_len = None
@ -345,7 +346,7 @@ class HttpFD(FileDownloader):
# Update file modification time # Update file modification time
if self.params.get('updatetime', True): if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None)) info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None))
self._hook_progress({ self._hook_progress({
'downloaded_bytes': byte_counter, 'downloaded_bytes': byte_counter,

View File

@ -2,9 +2,9 @@ import binascii
import io import io
import struct import struct
import time import time
import urllib.error
from .fragment import FragmentFD from .fragment import FragmentFD
from ..networking.exceptions import HTTPError
from ..utils import RetryManager from ..utils import RetryManager
u8 = struct.Struct('>B') u8 = struct.Struct('>B')
@ -271,7 +271,7 @@ class IsmFD(FragmentFD):
write_piff_header(ctx['dest_stream'], info_dict['_download_params']) write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
extra_state['ism_track_written'] = True extra_state['ism_track_written'] = True
self._append_fragment(ctx, frag_content) self._append_fragment(ctx, frag_content)
except urllib.error.HTTPError as err: except HTTPError as err:
retry.error = err retry.error = err
continue continue

View File

@ -5,13 +5,8 @@ import time
from . import get_suitable_downloader from . import get_suitable_downloader
from .common import FileDownloader from .common import FileDownloader
from .external import FFmpegFD from .external import FFmpegFD
from ..utils import ( from ..networking import Request
DownloadError, from ..utils import DownloadError, WebSocketsWrapper, str_or_none, try_get
WebSocketsWrapper,
sanitized_Request,
str_or_none,
try_get,
)
class NiconicoDmcFD(FileDownloader): class NiconicoDmcFD(FileDownloader):
@ -33,7 +28,7 @@ class NiconicoDmcFD(FileDownloader):
heartbeat_data = heartbeat_info_dict['data'].encode() heartbeat_data = heartbeat_info_dict['data'].encode()
heartbeat_interval = heartbeat_info_dict.get('interval', 30) heartbeat_interval = heartbeat_info_dict.get('interval', 30)
request = sanitized_Request(heartbeat_url, heartbeat_data) request = Request(heartbeat_url, heartbeat_data)
def heartbeat(): def heartbeat():
try: try:

View File

@ -1,8 +1,8 @@
import json import json
import time import time
import urllib.error
from .fragment import FragmentFD from .fragment import FragmentFD
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
RegexNotFoundError, RegexNotFoundError,
RetryManager, RetryManager,
@ -10,6 +10,7 @@ from ..utils import (
int_or_none, int_or_none,
try_get, try_get,
) )
from ..utils.networking import HTTPHeaderDict
class YoutubeLiveChatFD(FragmentFD): class YoutubeLiveChatFD(FragmentFD):
@ -37,10 +38,7 @@ class YoutubeLiveChatFD(FragmentFD):
start_time = int(time.time() * 1000) start_time = int(time.time() * 1000)
def dl_fragment(url, data=None, headers=None): def dl_fragment(url, data=None, headers=None):
http_headers = info_dict.get('http_headers', {}) http_headers = HTTPHeaderDict(info_dict.get('http_headers'), headers)
if headers:
http_headers = http_headers.copy()
http_headers.update(headers)
return self._download_fragment(ctx, url, info_dict, http_headers, data) return self._download_fragment(ctx, url, info_dict, http_headers, data)
def parse_actions_replay(live_chat_continuation): def parse_actions_replay(live_chat_continuation):
@ -129,7 +127,7 @@ class YoutubeLiveChatFD(FragmentFD):
or frag_index == 1 and try_refresh_replay_beginning or frag_index == 1 and try_refresh_replay_beginning
or parse_actions_replay) or parse_actions_replay)
return (True, *func(live_chat_continuation)) return (True, *func(live_chat_continuation))
except urllib.error.HTTPError as err: except HTTPError as err:
retry.error = err retry.error = err
continue continue
return False, None, None, None return False, None, None, None

View File

@ -22,7 +22,6 @@ from ..utils import (
int_or_none, int_or_none,
intlist_to_bytes, intlist_to_bytes,
OnDemandPagedList, OnDemandPagedList,
request_to_url,
time_seconds, time_seconds,
traverse_obj, traverse_obj,
update_url_query, update_url_query,
@ -137,7 +136,7 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey)) return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url): def abematv_license_open(self, url):
url = request_to_url(url) url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
ticket = urllib.parse.urlparse(url).netloc ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket) response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={ return urllib.response.addinfourl(io.BytesIO(response_data), headers={

View File

@ -6,10 +6,8 @@ import random
from .common import InfoExtractor from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import ( from ..compat import compat_b64decode
compat_HTTPError, from ..networking.exceptions import HTTPError
compat_b64decode,
)
from ..utils import ( from ..utils import (
ass_subtitles_timecode, ass_subtitles_timecode,
bytes_to_intlist, bytes_to_intlist,
@ -142,9 +140,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
self._HEADERS = {'authorization': 'Bearer ' + access_token} self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e: except ExtractorError as e:
message = None message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
resp = self._parse_json( resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {} e.cause.response.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code') message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE) self.report_warning(message or self._LOGIN_ERR_MESSAGE)
@ -195,14 +193,14 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
}) })
break break
except ExtractorError as e: except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError): if not isinstance(e.cause, HTTPError):
raise e raise e
if e.cause.code == 401: if e.cause.status == 401:
# This usually goes away with a different random pkcs1pad, so retry # This usually goes away with a different random pkcs1pad, so retry
continue continue
error = self._parse_json(e.cause.read(), video_id) error = self._parse_json(e.cause.response.read(), video_id)
message = error.get('message') message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country': if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message) self.raise_geo_restricted(msg=message)

View File

@ -2,11 +2,11 @@ import getpass
import json import json
import re import re
import time import time
import urllib.error
import xml.etree.ElementTree as etree import xml.etree.ElementTree as etree
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
NO_DEFAULT, NO_DEFAULT,
ExtractorError, ExtractorError,
@ -1394,7 +1394,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
form_page, urlh = form_page_res form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url') post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url): if not re.match(r'https?://', post_url):
post_url = compat_urlparse.urljoin(urlh.geturl(), post_url) post_url = compat_urlparse.urljoin(urlh.url, post_url)
form_data = self._hidden_inputs(form_page) form_data = self._hidden_inputs(form_page)
form_data.update(data) form_data.update(data)
return self._download_webpage_handle( return self._download_webpage_handle(
@ -1619,7 +1619,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history'] = 1 hidden_data['history'] = 1
provider_login_page_res = self._download_webpage_handle( provider_login_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending first bookend', urlh.url, video_id, 'Sending first bookend',
query=hidden_data) query=hidden_data)
provider_association_redirect, urlh = post_form( provider_association_redirect, urlh = post_form(
@ -1629,7 +1629,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}) })
provider_refresh_redirect_url = extract_redirect_url( provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl()) provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle( last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id, provider_refresh_redirect_url, video_id,
@ -1638,7 +1638,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history'] = 3 hidden_data['history'] = 3
mvpd_confirm_page_res = self._download_webpage_handle( mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending final bookend', urlh.url, video_id, 'Sending final bookend',
query=hidden_data) query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login') post_form(mvpd_confirm_page_res, 'Confirming Login')
@ -1652,7 +1652,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history_val'] = 1 hidden_data['history_val'] = 1
provider_login_redirect_page_res = self._download_webpage_handle( provider_login_redirect_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending First Bookend', urlh.url, video_id, 'Sending First Bookend',
query=hidden_data) query=hidden_data)
provider_login_redirect_page, urlh = provider_login_redirect_page_res provider_login_redirect_page, urlh = provider_login_redirect_page_res
@ -1680,7 +1680,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}) })
provider_refresh_redirect_url = extract_redirect_url( provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl()) provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle( last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id, provider_refresh_redirect_url, video_id,
@ -1690,7 +1690,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history_val'] = 3 hidden_data['history_val'] = 3
mvpd_confirm_page_res = self._download_webpage_handle( mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending Final Bookend', urlh.url, video_id, 'Sending Final Bookend',
query=hidden_data) query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login') post_form(mvpd_confirm_page_res, 'Confirming Login')
@ -1699,7 +1699,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
# based redirect that should be followed. # based redirect that should be followed.
provider_redirect_page, urlh = provider_redirect_page_res provider_redirect_page, urlh = provider_redirect_page_res
provider_refresh_redirect_url = extract_redirect_url( provider_refresh_redirect_url = extract_redirect_url(
provider_redirect_page, url=urlh.geturl()) provider_redirect_page, url=urlh.url)
if provider_refresh_redirect_url: if provider_refresh_redirect_url:
provider_redirect_page_res = self._download_webpage_handle( provider_redirect_page_res = self._download_webpage_handle(
provider_refresh_redirect_url, video_id, provider_refresh_redirect_url, video_id,
@ -1724,7 +1724,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
'requestor_id': requestor_id, 'requestor_id': requestor_id,
}), headers=mvpd_headers) }), headers=mvpd_headers)
except ExtractorError as e: except ExtractorError as e:
if not mso_id and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise_mvpd_required() raise_mvpd_required()
raise raise
if '<pendingLogout' in session: if '<pendingLogout' in session:

View File

@ -1,8 +1,8 @@
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
HEADRequest,
ExtractorError, ExtractorError,
determine_ext, determine_ext,
scale_thumbnails_to_max_format_width, scale_thumbnails_to_max_format_width,
@ -121,7 +121,7 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
canonical_url = self._request_webpage( canonical_url = self._request_webpage(
HEADRequest(url), video_id, HEADRequest(url), video_id,
note='Resolve canonical player URL', note='Resolve canonical player URL',
errnote='Could not resolve canonical player URL').geturl() errnote='Could not resolve canonical player URL').url
_, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url) _, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
cid = urllib.parse.parse_qs(query)['cid'][0] cid = urllib.parse.parse_qs(query)['cid'][0]

View File

@ -1,16 +1,16 @@
import json import json
import re import re
import urllib.error
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from .naver import NaverBaseIE from .naver import NaverBaseIE
from .youtube import YoutubeBaseInfoExtractor, YoutubeIE from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
from ..compat import compat_HTTPError, compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
KNOWN_EXTENSIONS, KNOWN_EXTENSIONS,
ExtractorError, ExtractorError,
HEADRequest,
bug_reports_message, bug_reports_message,
clean_html, clean_html,
dict_get, dict_get,
@ -899,7 +899,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
video_id, note='Fetching archived video file url', expected_status=True) video_id, note='Fetching archived video file url', expected_status=True)
except ExtractorError as e: except ExtractorError as e:
# HTTP Error 404 is expected if the video is not saved. # HTTP Error 404 is expected if the video is not saved.
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: if isinstance(e.cause, HTTPError) and e.cause.status == 404:
self.raise_no_formats( self.raise_no_formats(
'The requested video is not archived, indexed, or there is an issue with web.archive.org (try again later)', expected=True) 'The requested video is not archived, indexed, or there is an issue with web.archive.org (try again later)', expected=True)
else: else:
@ -926,7 +926,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
info['thumbnails'] = self._extract_thumbnails(video_id) info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh: if urlh:
url = compat_urllib_parse_unquote(urlh.geturl()) url = compat_urllib_parse_unquote(urlh.url)
video_file_url_qs = parse_qs(url) video_file_url_qs = parse_qs(url)
# Attempt to recover any ext & format info from playback url & response headers # Attempt to recover any ext & format info from playback url & response headers
format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))} format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
@ -1052,7 +1052,7 @@ class VLiveWebArchiveIE(InfoExtractor):
try: try:
return self._download_webpage(f'https://web.archive.org/web/{timestamp}id_/{url}', video_id, **kwargs) return self._download_webpage(f'https://web.archive.org/web/{timestamp}id_/{url}', video_id, **kwargs)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404: if isinstance(e.cause, HTTPError) and e.cause.status == 404:
raise ExtractorError('Page was not archived', expected=True) raise ExtractorError('Page was not archived', expected=True)
retry.error = e retry.error = e
continue continue

View File

@ -1,5 +1,5 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -34,8 +34,8 @@ class AtresPlayerIE(InfoExtractor):
_API_BASE = 'https://api.atresplayer.com/' _API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code): def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code: if isinstance(e.cause, HTTPError) and e.cause.status == code:
error = self._parse_json(e.cause.read(), None) error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered': if error.get('error') == 'required_registered':
self.raise_login_required() self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True) raise ExtractorError(error['error_description'], expected=True)

View File

@ -2,11 +2,11 @@ import functools
import itertools import itertools
import json import json
import re import re
import urllib.error
import xml.etree.ElementTree import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str, compat_urlparse from ..compat import compat_str, compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
OnDemandPagedList, OnDemandPagedList,
@ -277,7 +277,7 @@ class BBCCoUkIE(InfoExtractor):
post_url, None, 'Logging in', data=urlencode_postdata(login_form), post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL}) headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl(): if self._LOGIN_URL in urlh.url:
error = clean_html(get_element_by_class('form-message', response)) error = clean_html(get_element_by_class('form-message', response))
if error: if error:
raise ExtractorError( raise ExtractorError(
@ -388,8 +388,8 @@ class BBCCoUkIE(InfoExtractor):
href, programme_id, ext='mp4', entry_protocol='m3u8_native', href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False) m3u8_id=format_id, fatal=False)
except ExtractorError as e: except ExtractorError as e:
if not (isinstance(e.exc_info[1], urllib.error.HTTPError) if not (isinstance(e.exc_info[1], HTTPError)
and e.exc_info[1].code in (403, 404)): and e.exc_info[1].status in (403, 404)):
raise raise
fmts = [] fmts = []
formats.extend(fmts) formats.extend(fmts)
@ -472,7 +472,7 @@ class BBCCoUkIE(InfoExtractor):
return programme_id, title, description, duration, formats, subtitles return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee: except ExtractorError as ee:
if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): if not (isinstance(ee.cause, HTTPError) and ee.cause.status == 404):
raise raise
# fallback to legacy playlist # fallback to legacy playlist
@ -983,7 +983,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
# Some playlist URL may fail with 500, at the same time # Some playlist URL may fail with 500, at the same time
# the other one may work fine (e.g. # the other one may work fine (e.g.
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500: if isinstance(e.cause, HTTPError) and e.cause.status == 500:
continue continue
raise raise
if entry: if entry:

View File

@ -4,11 +4,11 @@ import hashlib
import itertools import itertools
import math import math
import time import time
import urllib.error
import urllib.parse import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor from .common import InfoExtractor, SearchInfoExtractor
from ..dependencies import Cryptodome from ..dependencies import Cryptodome
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
GeoRestrictedError, GeoRestrictedError,
@ -614,7 +614,7 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search', response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search',
playlist_id, note=f'Downloading page {page_idx}', query=query) playlist_id, note=f'Downloading page {page_idx}', query=query)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 412: if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError( raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True) 'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
raise raise

View File

@ -2,9 +2,9 @@ import functools
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
OnDemandPagedList, OnDemandPagedList,
clean_html, clean_html,
get_element_by_class, get_element_by_class,

View File

@ -1,6 +1,6 @@
from .adobepass import AdobePassIE from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
HEADRequest,
extract_attributes, extract_attributes,
float_or_none, float_or_none,
get_element_html_by_class, get_element_html_by_class,
@ -155,7 +155,7 @@ class BravoTVIE(AdobePassIE):
chapters = None chapters = None
m3u8_url = self._request_webpage(HEADRequest( m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').geturl() update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url: if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id) self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls') formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')

View File

@ -7,10 +7,10 @@ from .adobepass import AdobePassIE
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_etree_fromstring, compat_etree_fromstring,
compat_HTTPError,
compat_parse_qs, compat_parse_qs,
compat_urlparse, compat_urlparse,
) )
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
clean_html, clean_html,
dict_get, dict_get,
@ -915,8 +915,8 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
json_data = self._download_json(api_url, video_id, headers=headers) json_data = self._download_json(api_url, video_id, headers=headers)
break break
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
json_data = self._parse_json(e.cause.read().decode(), video_id)[0] json_data = self._parse_json(e.cause.response.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code'] message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO': if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message) self.raise_geo_restricted(msg=message)

View File

@ -64,7 +64,7 @@ class CanalplusIE(InfoExtractor):
# response = self._request_webpage( # response = self._request_webpage(
# HEADRequest(fmt_url), video_id, # HEADRequest(fmt_url), video_id,
# 'Checking if the video is georestricted') # 'Checking if the video is georestricted')
# if '/blocage' in response.geturl(): # if '/blocage' in response.url:
# raise ExtractorError( # raise ExtractorError(
# 'The video is not available in your country', # 'The video is not available in your country',
# expected=True) # expected=True)

View File

@ -7,9 +7,9 @@ import zlib
from .anvato import AnvatoIE from .anvato import AnvatoIE
from .common import InfoExtractor from .common import InfoExtractor
from .paramountplus import ParamountPlusIE from .paramountplus import ParamountPlusIE
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
UserNotLive, UserNotLive,
determine_ext, determine_ext,
float_or_none, float_or_none,

View File

@ -1,20 +1,20 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_urllib_parse_unquote, compat_urllib_parse_urlparse
compat_urllib_parse_unquote, from ..networking import Request
compat_urllib_parse_urlparse,
)
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
float_or_none, float_or_none,
sanitized_Request,
str_or_none, str_or_none,
traverse_obj, traverse_obj,
urlencode_postdata, urlencode_postdata,
USER_AGENTS,
) )
USER_AGENTS = {
'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
}
class CeskaTelevizeIE(InfoExtractor): class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)' _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
@ -97,7 +97,7 @@ class CeskaTelevizeIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id) webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = compat_urllib_parse_urlparse(urlh.geturl()) parsed_url = compat_urllib_parse_urlparse(urlh.url)
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize') site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None) playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title: if site_name and playlist_title:
@ -163,16 +163,16 @@ class CeskaTelevizeIE(InfoExtractor):
entries = [] entries = []
for user_agent in (None, USER_AGENTS['Safari']): for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request( req = Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/', 'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data)) data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded') req.headers['Content-type'] = 'application/x-www-form-urlencoded'
req.add_header('x-addr', '127.0.0.1') req.headers['x-addr'] = '127.0.0.1'
req.add_header('X-Requested-With', 'XMLHttpRequest') req.headers['X-Requested-With'] = 'XMLHttpRequest'
if user_agent: if user_agent:
req.add_header('User-Agent', user_agent) req.headers['User-Agent'] = user_agent
req.add_header('Referer', url) req.headers['Referer'] = url
playlistpage = self._download_json(req, playlist_id, fatal=False) playlistpage = self._download_json(req, playlist_id, fatal=False)
@ -183,8 +183,8 @@ class CeskaTelevizeIE(InfoExtractor):
if playlist_url == 'error_region': if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) req = Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url) req.headers['Referer'] = url
playlist = self._download_json(req, playlist_id, fatal=False) playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist: if not playlist:

View File

@ -1,6 +1,6 @@
import json import json
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
float_or_none, float_or_none,
@ -40,7 +40,7 @@ class CinetecaMilanoIE(InfoExtractor):
'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or '' 'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or ''
}) })
except ExtractorError as e: except ExtractorError as e:
if ((isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 500) if ((isinstance(e.cause, HTTPError) and e.cause.status == 500)
or isinstance(e.cause, json.JSONDecodeError)): or isinstance(e.cause, json.JSONDecodeError)):
self.raise_login_required(method='cookies') self.raise_login_required(method='cookies')
raise raise

View File

@ -33,7 +33,7 @@ class CiscoWebexIE(InfoExtractor):
if rcid: if rcid:
webpage = self._download_webpage(url, None, note='Getting video ID') webpage = self._download_webpage(url, None, note='Getting video ID')
url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url') url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url')
url = self._request_webpage(url, None, note='Resolving final URL').geturl() url = self._request_webpage(url, None, note='Resolving final URL').url
mobj = self._match_valid_url(url) mobj = self._match_valid_url(url)
subdomain = mobj.group('subdomain') subdomain = mobj.group('subdomain')
siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2') siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2')
@ -49,7 +49,7 @@ class CiscoWebexIE(InfoExtractor):
'https://%s.webex.com/webappng/api/v1/recordings/%s/stream' % (subdomain, video_id), 'https://%s.webex.com/webappng/api/v1/recordings/%s/stream' % (subdomain, video_id),
video_id, headers=headers, query={'siteurl': siteurl}, expected_status=(403, 429)) video_id, headers=headers, query={'siteurl': siteurl}, expected_status=(403, 429))
if urlh.getcode() == 403: if urlh.status == 403:
if stream['code'] == 53004: if stream['code'] == 53004:
self.raise_login_required() self.raise_login_required()
if stream['code'] == 53005: if stream['code'] == 53005:
@ -59,7 +59,7 @@ class CiscoWebexIE(InfoExtractor):
'This video is protected by a password, use the --video-password option', expected=True) 'This video is protected by a password, use the --video-password option', expected=True)
raise ExtractorError(f'{self.IE_NAME} said: {stream["code"]} - {stream["message"]}', expected=True) raise ExtractorError(f'{self.IE_NAME} said: {stream["code"]} - {stream["message"]}', expected=True)
if urlh.getcode() == 429: if urlh.status == 429:
self.raise_login_required( self.raise_login_required(
f'{self.IE_NAME} asks you to solve a CAPTCHA. Solve CAPTCHA in browser and', f'{self.IE_NAME} asks you to solve a CAPTCHA. Solve CAPTCHA in browser and',
method='cookies') method='cookies')

View File

@ -31,8 +31,12 @@ from ..compat import (
from ..cookies import LenientSimpleCookie from ..cookies import LenientSimpleCookie
from ..downloader.f4m import get_base_url, remove_encrypted_media from ..downloader.f4m import get_base_url, remove_encrypted_media
from ..downloader.hls import HlsFD from ..downloader.hls import HlsFD
from ..networking.common import HEADRequest, Request from ..networking import HEADRequest, Request
from ..networking.exceptions import network_exceptions from ..networking.exceptions import (
HTTPError,
IncompleteRead,
network_exceptions,
)
from ..utils import ( from ..utils import (
IDENTITY, IDENTITY,
JSON_LD_RE, JSON_LD_RE,
@ -729,7 +733,7 @@ class InfoExtractor:
e.ie = e.ie or self.IE_NAME, e.ie = e.ie or self.IE_NAME,
e.traceback = e.traceback or sys.exc_info()[2] e.traceback = e.traceback or sys.exc_info()[2]
raise raise
except http.client.IncompleteRead as e: except IncompleteRead as e:
raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url)) raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url))
except (KeyError, StopIteration) as e: except (KeyError, StopIteration) as e:
raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url)) raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url))
@ -788,16 +792,19 @@ class InfoExtractor:
@staticmethod @staticmethod
def __can_accept_status_code(err, expected_status): def __can_accept_status_code(err, expected_status):
assert isinstance(err, urllib.error.HTTPError) assert isinstance(err, HTTPError)
if expected_status is None: if expected_status is None:
return False return False
elif callable(expected_status): elif callable(expected_status):
return expected_status(err.code) is True return expected_status(err.status) is True
else: else:
return err.code in variadic(expected_status) return err.status in variadic(expected_status)
def _create_request(self, url_or_request, data=None, headers=None, query=None): def _create_request(self, url_or_request, data=None, headers=None, query=None):
if isinstance(url_or_request, urllib.request.Request): if isinstance(url_or_request, urllib.request.Request):
self._downloader.deprecation_warning(
'Passing a urllib.request.Request to _create_request() is deprecated. '
'Use yt_dlp.networking.common.Request instead.')
url_or_request = urllib_req_to_req(url_or_request) url_or_request = urllib_req_to_req(url_or_request)
elif not isinstance(url_or_request, Request): elif not isinstance(url_or_request, Request):
url_or_request = Request(url_or_request) url_or_request = Request(url_or_request)
@ -839,7 +846,7 @@ class InfoExtractor:
try: try:
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query)) return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query))
except network_exceptions as err: except network_exceptions as err:
if isinstance(err, urllib.error.HTTPError): if isinstance(err, HTTPError):
if self.__can_accept_status_code(err, expected_status): if self.__can_accept_status_code(err, expected_status):
return err.response return err.response
@ -973,11 +980,11 @@ class InfoExtractor:
if prefix is not None: if prefix is not None:
webpage_bytes = prefix + webpage_bytes webpage_bytes = prefix + webpage_bytes
if self.get_param('dump_intermediate_pages', False): if self.get_param('dump_intermediate_pages', False):
self.to_screen('Dumping request to ' + urlh.geturl()) self.to_screen('Dumping request to ' + urlh.url)
dump = base64.b64encode(webpage_bytes).decode('ascii') dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump) self._downloader.to_screen(dump)
if self.get_param('write_pages'): if self.get_param('write_pages'):
filename = self._request_dump_filename(urlh.geturl(), video_id) filename = self._request_dump_filename(urlh.url, video_id)
self.to_screen(f'Saving request to {filename}') self.to_screen(f'Saving request to {filename}')
with open(filename, 'wb') as outf: with open(filename, 'wb') as outf:
outf.write(webpage_bytes) outf.write(webpage_bytes)
@ -1109,7 +1116,7 @@ class InfoExtractor:
while True: while True:
try: try:
return self.__download_webpage(url_or_request, video_id, note, errnote, None, fatal, *args, **kwargs) return self.__download_webpage(url_or_request, video_id, note, errnote, None, fatal, *args, **kwargs)
except http.client.IncompleteRead as e: except IncompleteRead as e:
try_count += 1 try_count += 1
if try_count >= tries: if try_count >= tries:
raise e raise e
@ -1806,7 +1813,7 @@ class InfoExtractor:
return [] return []
manifest, urlh = res manifest, urlh = res
manifest_url = urlh.geturl() manifest_url = urlh.url
return self._parse_f4m_formats( return self._parse_f4m_formats(
manifest, manifest_url, video_id, preference=preference, quality=quality, f4m_id=f4m_id, manifest, manifest_url, video_id, preference=preference, quality=quality, f4m_id=f4m_id,
@ -1965,7 +1972,7 @@ class InfoExtractor:
return [], {} return [], {}
m3u8_doc, urlh = res m3u8_doc, urlh = res
m3u8_url = urlh.geturl() m3u8_url = urlh.url
return self._parse_m3u8_formats_and_subtitles( return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol, m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
@ -2243,7 +2250,7 @@ class InfoExtractor:
return [], {} return [], {}
smil, urlh = res smil, urlh = res
smil_url = urlh.geturl() smil_url = urlh.url
namespace = self._parse_smil_namespace(smil) namespace = self._parse_smil_namespace(smil)
@ -2266,7 +2273,7 @@ class InfoExtractor:
return {} return {}
smil, urlh = res smil, urlh = res
smil_url = urlh.geturl() smil_url = urlh.url
return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
@ -2458,7 +2465,7 @@ class InfoExtractor:
return [] return []
xspf, urlh = res xspf, urlh = res
xspf_url = urlh.geturl() xspf_url = urlh.url
return self._parse_xspf( return self._parse_xspf(
xspf, playlist_id, xspf_url=xspf_url, xspf, playlist_id, xspf_url=xspf_url,
@ -2529,7 +2536,7 @@ class InfoExtractor:
return [], {} return [], {}
# We could have been redirected to a new url when we retrieved our mpd file. # We could have been redirected to a new url when we retrieved our mpd file.
mpd_url = urlh.geturl() mpd_url = urlh.url
mpd_base_url = base_url(mpd_url) mpd_base_url = base_url(mpd_url)
return self._parse_mpd_formats_and_subtitles( return self._parse_mpd_formats_and_subtitles(
@ -2900,7 +2907,7 @@ class InfoExtractor:
if ism_doc is None: if ism_doc is None:
return [], {} return [], {}
return self._parse_ism_formats_and_subtitles(ism_doc, urlh.geturl(), ism_id) return self._parse_ism_formats_and_subtitles(ism_doc, urlh.url, ism_id)
def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None): def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None):
""" """

View File

@ -4,7 +4,7 @@ import re
import time import time
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
float_or_none, float_or_none,
@ -113,7 +113,7 @@ class CrackleIE(InfoExtractor):
errnote='Unable to download media JSON') errnote='Unable to download media JSON')
except ExtractorError as e: except ExtractorError as e:
# 401 means geo restriction, trying next country # 401 means geo restriction, trying next country
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
continue continue
raise raise

View File

@ -1,7 +1,7 @@
import base64 import base64
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
float_or_none, float_or_none,
@ -114,7 +114,7 @@ class CrunchyrollBaseIE(InfoExtractor):
result = self._call_base_api( result = self._call_base_api(
path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query) path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query)
except ExtractorError as error: except ExtractorError as error:
if isinstance(error.cause, urllib.error.HTTPError) and error.cause.code == 404: if isinstance(error.cause, HTTPError) and error.cause.status == 404:
return None return None
raise raise

View File

@ -1,10 +1,8 @@
import time import time
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..networking import HEADRequest
int_or_none, from ..utils import int_or_none
HEADRequest,
)
class CultureUnpluggedIE(InfoExtractor): class CultureUnpluggedIE(InfoExtractor):

View File

@ -1,9 +1,9 @@
import hashlib import hashlib
import re import re
import time import time
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
classproperty, classproperty,
@ -105,7 +105,7 @@ class DacastVODIE(DacastBaseIE):
formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls') formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls')
except ExtractorError as e: except ExtractorError as e:
# CDN will randomly respond with 403 # CDN will randomly respond with 403
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
retry.error = e retry.error = e
continue continue
raise raise

View File

@ -3,7 +3,7 @@ import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
OnDemandPagedList, OnDemandPagedList,
@ -68,9 +68,9 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
None, 'Downloading Access Token', None, 'Downloading Access Token',
data=urlencode_postdata(data))['access_token'] data=urlencode_postdata(data))['access_token']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise ExtractorError(self._parse_json( raise ExtractorError(self._parse_json(
e.cause.read().decode(), xid)['error_description'], expected=True) e.cause.response.read().decode(), xid)['error_description'], expected=True)
raise raise
self._set_dailymotion_cookie('access_token' if username else 'client_token', token) self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
self._HEADERS['Authorization'] = 'Bearer ' + token self._HEADERS['Authorization'] = 'Bearer ' + token

View File

@ -3,8 +3,8 @@ import string
from .discoverygo import DiscoveryGoBaseIE from .discoverygo import DiscoveryGoBaseIE
from ..compat import compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError from ..utils import ExtractorError
from ..compat import compat_HTTPError
class DiscoveryIE(DiscoveryGoBaseIE): class DiscoveryIE(DiscoveryGoBaseIE):
@ -100,9 +100,9 @@ class DiscoveryIE(DiscoveryGoBaseIE):
self._API_BASE_URL + 'streaming/video/' + video_id, self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, 'Downloading streaming JSON metadata', headers=headers) display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
e_description = self._parse_json( e_description = self._parse_json(
e.cause.read().decode(), display_id)['description'] e.cause.response.read().decode(), display_id)['description']
if 'resource not available for country' in e_description: if 'resource not available for country' in e_description:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES) self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
if 'Authorized Networks' in e_description: if 'Authorized Networks' in e_description:

View File

@ -2,7 +2,7 @@ import json
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
@ -39,7 +39,7 @@ class DPlayBaseIE(InfoExtractor):
return f'Bearer {token}' return f'Bearer {token}'
def _process_errors(self, e, geo_countries): def _process_errors(self, e, geo_countries):
info = self._parse_json(e.cause.read().decode('utf-8'), None) info = self._parse_json(e.cause.response.read().decode('utf-8'), None)
error = info['errors'][0] error = info['errors'][0]
error_code = error.get('code') error_code = error.get('code')
if error_code == 'access.denied.geoblocked': if error_code == 'access.denied.geoblocked':
@ -87,7 +87,7 @@ class DPlayBaseIE(InfoExtractor):
'include': 'images,primaryChannel,show,tags' 'include': 'images,primaryChannel,show,tags'
}) })
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: if isinstance(e.cause, HTTPError) and e.cause.status == 400:
self._process_errors(e, geo_countries) self._process_errors(e, geo_countries)
raise raise
video_id = video['data']['id'] video_id = video['data']['id']
@ -99,7 +99,7 @@ class DPlayBaseIE(InfoExtractor):
streaming = self._download_video_playback_info( streaming = self._download_video_playback_info(
disco_base, video_id, headers) disco_base, video_id, headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
self._process_errors(e, geo_countries) self._process_errors(e, geo_countries)
raise raise
for format_dict in streaming: for format_dict in streaming:

View File

@ -2,7 +2,7 @@ import functools
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -111,8 +111,8 @@ class EaglePlatformIE(InfoExtractor):
response = super(EaglePlatformIE, self)._download_json( response = super(EaglePlatformIE, self)._download_json(
url_or_request, video_id, *args, **kwargs) url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee: except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError): if isinstance(ee.cause, HTTPError):
response = self._parse_json(ee.cause.read().decode('utf-8'), video_id) response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
self._handle_error(response) self._handle_error(response)
raise raise
return response return response

View File

@ -1,10 +1,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..networking import Request
float_or_none, from ..utils import float_or_none, int_or_none, parse_iso8601
int_or_none,
parse_iso8601,
sanitized_Request,
)
class EitbIE(InfoExtractor): class EitbIE(InfoExtractor):
@ -54,7 +50,7 @@ class EitbIE(InfoExtractor):
hls_url = media.get('HLS_SURL') hls_url = media.get('HLS_SURL')
if hls_url: if hls_url:
request = sanitized_Request( request = Request(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/', 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
headers={'Referer': url}) headers={'Referer': url})
token_data = self._download_json( token_data = self._download_json(

View File

@ -52,7 +52,7 @@ class EpornerIE(InfoExtractor):
webpage, urlh = self._download_webpage_handle(url, display_id) webpage, urlh = self._download_webpage_handle(url, display_id)
video_id = self._match_id(urlh.geturl()) video_id = self._match_id(urlh.url)
hash = self._search_regex( hash = self._search_regex(
r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash') r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash')

View File

@ -8,6 +8,8 @@ from ..compat import (
compat_str, compat_str,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
) )
from ..networking import Request
from ..networking.exceptions import network_exceptions
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
clean_html, clean_html,
@ -19,11 +21,9 @@ from ..utils import (
int_or_none, int_or_none,
js_to_json, js_to_json,
merge_dicts, merge_dicts,
network_exceptions,
parse_count, parse_count,
parse_qs, parse_qs,
qualities, qualities,
sanitized_Request,
traverse_obj, traverse_obj,
try_get, try_get,
url_or_none, url_or_none,
@ -319,7 +319,7 @@ class FacebookIE(InfoExtractor):
} }
def _perform_login(self, username, password): def _perform_login(self, username, password):
login_page_req = sanitized_Request(self._LOGIN_URL) login_page_req = Request(self._LOGIN_URL)
self._set_cookie('facebook.com', 'locale', 'en_US') self._set_cookie('facebook.com', 'locale', 'en_US')
login_page = self._download_webpage(login_page_req, None, login_page = self._download_webpage(login_page_req, None,
note='Downloading login page', note='Downloading login page',
@ -340,8 +340,8 @@ class FacebookIE(InfoExtractor):
'timezone': '-60', 'timezone': '-60',
'trynum': '1', 'trynum': '1',
} }
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) request = Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
try: try:
login_results = self._download_webpage(request, None, login_results = self._download_webpage(request, None,
note='Logging in', errnote='unable to fetch login page') note='Logging in', errnote='unable to fetch login page')
@ -367,8 +367,8 @@ class FacebookIE(InfoExtractor):
'h': h, 'h': h,
'name_action_selected': 'dont_save', 'name_action_selected': 'dont_save',
} }
check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) check_req = Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') check_req.headers['Content-Type'] = 'application/x-www-form-urlencoded'
check_response = self._download_webpage(check_req, None, check_response = self._download_webpage(check_req, None,
note='Confirming login') note='Confirming login')
if re.search(r'id="checkpointSubmitButton"', check_response) is not None: if re.search(r'id="checkpointSubmitButton"', check_response) is not None:

View File

@ -3,11 +3,11 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_parse_qs from ..compat import compat_parse_qs
from ..dependencies import websockets from ..dependencies import websockets
from ..networking import Request
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
WebSocketsWrapper, WebSocketsWrapper,
js_to_json, js_to_json,
sanitized_Request,
traverse_obj, traverse_obj,
update_url_query, update_url_query,
urlencode_postdata, urlencode_postdata,
@ -57,7 +57,7 @@ class FC2IE(InfoExtractor):
} }
login_data = urlencode_postdata(login_form_strs) login_data = urlencode_postdata(login_form_strs)
request = sanitized_Request( request = Request(
'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data) 'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in') login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
@ -66,7 +66,7 @@ class FC2IE(InfoExtractor):
return False return False
# this is also needed # this is also needed
login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done') login_redir = Request('http://id.fc2.com/?mode=redirect&login=done')
self._download_webpage( self._download_webpage(
login_redir, None, note='Login redirect', errnote='Login redirect failed') login_redir, None, note='Login redirect', errnote='Login redirect failed')

View File

@ -1,8 +1,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_str
compat_str, from ..networking.exceptions import HTTPError
compat_HTTPError,
)
from ..utils import ( from ..utils import (
qualities, qualities,
strip_or_none, strip_or_none,
@ -40,8 +38,8 @@ class FilmOnIE(InfoExtractor):
'https://www.filmon.com/api/vod/movie?id=%s' % video_id, 'https://www.filmon.com/api/vod/movie?id=%s' % video_id,
video_id)['response'] video_id)['response']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError): if isinstance(e.cause, HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason'] errmsg = self._parse_json(e.cause.response.read().decode(), video_id)['reason']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise raise
@ -124,8 +122,8 @@ class FilmOnChannelIE(InfoExtractor):
channel_data = self._download_json( channel_data = self._download_json(
'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data'] 'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError): if isinstance(e.cause, HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message'] errmsg = self._parse_json(e.cause.response.read().decode(), channel_id)['message']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise raise

View File

@ -3,10 +3,10 @@ import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_HTTPError,
compat_str, compat_str,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
) )
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -68,9 +68,9 @@ class FOXIE(InfoExtractor):
'https://api3.fox.com/v2.0/' + path, 'https://api3.fox.com/v2.0/' + path,
video_id, data=data, headers=headers) video_id, data=data, headers=headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
entitlement_issues = self._parse_json( entitlement_issues = self._parse_json(
e.cause.read().decode(), video_id)['entitlementIssues'] e.cause.response.read().decode(), video_id)['entitlementIssues']
for e in entitlement_issues: for e in entitlement_issues:
if e.get('errorCode') == 1005: if e.get('errorCode') == 1005:
raise ExtractorError( raise ExtractorError(
@ -123,8 +123,8 @@ class FOXIE(InfoExtractor):
try: try:
m3u8_url = self._download_json(release_url, video_id)['playURL'] m3u8_url = self._download_json(release_url, video_id)['playURL']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.read().decode(), video_id) error = self._parse_json(e.cause.response.read().decode(), video_id)
if error.get('exception') == 'GeoLocationBlocked': if error.get('exception') == 'GeoLocationBlocked':
self.raise_geo_restricted(countries=['US']) self.raise_geo_restricted(countries=['US'])
raise ExtractorError(error['description'], expected=True) raise ExtractorError(error['description'], expected=True)

View File

@ -1,6 +1,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from .uplynk import UplynkPreplayIE from .uplynk import UplynkPreplayIE
from ..utils import HEADRequest, float_or_none, make_archive_id, smuggle_url from ..networking import HEADRequest
from ..utils import float_or_none, make_archive_id, smuggle_url
class FoxSportsIE(InfoExtractor): class FoxSportsIE(InfoExtractor):
@ -35,7 +36,7 @@ class FoxSportsIE(InfoExtractor):
'x-api-key': 'cf289e299efdfa39fb6316f259d1de93', 'x-api-key': 'cf289e299efdfa39fb6316f259d1de93',
}) })
preplay_url = self._request_webpage( preplay_url = self._request_webpage(
HEADRequest(data['url']), video_id, 'Fetching preplay URL').geturl() HEADRequest(data['url']), video_id, 'Fetching preplay URL').url
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',

View File

@ -1,5 +1,5 @@
from ..utils import HEADRequest
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
class FujiTVFODPlus7IE(InfoExtractor): class FujiTVFODPlus7IE(InfoExtractor):

View File

@ -3,7 +3,7 @@ import re
import string import string
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
@ -46,8 +46,8 @@ class FunimationBaseIE(InfoExtractor):
})) }))
FunimationBaseIE._TOKEN = data['token'] FunimationBaseIE._TOKEN = data['token']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
error = self._parse_json(e.cause.read().decode(), None)['error'] error = self._parse_json(e.cause.response.read().decode(), None)['error']
raise ExtractorError(error, expected=True) raise ExtractorError(error, expected=True)
raise raise

View File

@ -2,13 +2,8 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from .kaltura import KalturaIE from .kaltura import KalturaIE
from ..utils import ( from ..networking import HEADRequest, Request
HEADRequest, from ..utils import remove_start, smuggle_url, urlencode_postdata
remove_start,
sanitized_Request,
smuggle_url,
urlencode_postdata,
)
class GDCVaultIE(InfoExtractor): class GDCVaultIE(InfoExtractor):
@ -138,8 +133,8 @@ class GDCVaultIE(InfoExtractor):
'password': password, 'password': password,
} }
request = sanitized_Request(login_url, urlencode_postdata(login_form)) request = Request(login_url, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
self._download_webpage(request, display_id, 'Logging in') self._download_webpage(request, display_id, 'Logging in')
start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page') start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
self._download_webpage(logout_url, display_id, 'Logging out') self._download_webpage(logout_url, display_id, 'Logging out')
@ -163,7 +158,7 @@ class GDCVaultIE(InfoExtractor):
video_url = 'http://www.gdcvault.com' + direct_url video_url = 'http://www.gdcvault.com' + direct_url
# resolve the url so that we can detect the correct extension # resolve the url so that we can detect the correct extension
video_url = self._request_webpage( video_url = self._request_webpage(
HEADRequest(video_url), video_id).geturl() HEADRequest(video_url), video_id).url
return { return {
'id': video_id, 'id': video_id,

View File

@ -2431,7 +2431,7 @@ class GenericIE(InfoExtractor):
'Accept-Encoding': 'identity', 'Accept-Encoding': 'identity',
**smuggled_data.get('http_headers', {}) **smuggled_data.get('http_headers', {})
}) })
new_url = full_response.geturl() new_url = full_response.url
url = urllib.parse.urlparse(url)._replace(scheme=urllib.parse.urlparse(new_url).scheme).geturl() url = urllib.parse.urlparse(url)._replace(scheme=urllib.parse.urlparse(new_url).scheme).geturl()
if new_url != extract_basic_auth(url)[0]: if new_url != extract_basic_auth(url)[0]:
self.report_following_redirect(new_url) self.report_following_redirect(new_url)
@ -2529,12 +2529,12 @@ class GenericIE(InfoExtractor):
return self.playlist_result( return self.playlist_result(
self._parse_xspf( self._parse_xspf(
doc, video_id, xspf_url=url, doc, video_id, xspf_url=url,
xspf_base_url=full_response.geturl()), xspf_base_url=full_response.url),
video_id) video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles( info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
doc, doc,
mpd_base_url=full_response.geturl().rpartition('/')[0], mpd_base_url=full_response.url.rpartition('/')[0],
mpd_url=url) mpd_url=url)
self._extra_manifest_info(info_dict, url) self._extra_manifest_info(info_dict, url)
self.report_detected('DASH manifest') self.report_detected('DASH manifest')
@ -2572,7 +2572,7 @@ class GenericIE(InfoExtractor):
info_dict = types.MappingProxyType(info_dict) # Prevents accidental mutation info_dict = types.MappingProxyType(info_dict) # Prevents accidental mutation
video_id = traverse_obj(info_dict, 'display_id', 'id') or self._generic_id(url) video_id = traverse_obj(info_dict, 'display_id', 'id') or self._generic_id(url)
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
actual_url = urlh.geturl() if urlh else url actual_url = urlh.url if urlh else url
# Sometimes embedded video player is hidden behind percent encoding # Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)

View File

@ -8,8 +8,8 @@ from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_str, compat_str,
) )
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
HEADRequest,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
orderedSet, orderedSet,

View File

@ -228,7 +228,7 @@ class GoogleDriveIE(InfoExtractor):
# Using original URLs may result in redirect loop due to # Using original URLs may result in redirect loop due to
# google.com's cookies mistakenly used for googleusercontent.com # google.com's cookies mistakenly used for googleusercontent.com
# redirect URLs (see #23919). # redirect URLs (see #23919).
'url': urlh.geturl(), 'url': urlh.url,
'ext': determine_ext(title, 'mp4').lower(), 'ext': determine_ext(title, 'mp4').lower(),
'format_id': 'source', 'format_id': 'source',
'quality': 1, 'quality': 1,

View File

@ -126,7 +126,7 @@ class HKETVIE(InfoExtractor):
# If we ever wanted to provide the final resolved URL that # If we ever wanted to provide the final resolved URL that
# does not require cookies, albeit with a shorter lifespan: # does not require cookies, albeit with a shorter lifespan:
# urlh = self._downloader.urlopen(file_url) # urlh = self._downloader.urlopen(file_url)
# resolved_url = urlh.geturl() # resolved_url = urlh.url
label = fmt.get('label') label = fmt.get('label')
h = self._FORMAT_HEIGHTS.get(label) h = self._FORMAT_HEIGHTS.get(label)
w = h * width // height if h and width and height else None w = h * width // height if h and width and height else None

View File

@ -1,11 +1,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_b64decode from ..compat import compat_b64decode
from ..utils import ( from ..networking import HEADRequest, Request
ExtractorError, from ..utils import ExtractorError, urlencode_postdata
HEADRequest,
sanitized_Request,
urlencode_postdata,
)
class HotNewHipHopIE(InfoExtractor): class HotNewHipHopIE(InfoExtractor):
@ -36,9 +32,9 @@ class HotNewHipHopIE(InfoExtractor):
('mediaType', 's'), ('mediaType', 's'),
('mediaId', video_id), ('mediaId', video_id),
]) ])
r = sanitized_Request( r = Request(
'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata) 'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
r.add_header('Content-Type', 'application/x-www-form-urlencoded') r.headers['Content-Type'] = 'application/x-www-form-urlencoded'
mkd = self._download_json( mkd = self._download_json(
r, video_id, note='Requesting media key', r, video_id, note='Requesting media key',
errnote='Could not download media key') errnote='Could not download media key')
@ -50,7 +46,7 @@ class HotNewHipHopIE(InfoExtractor):
req = self._request_webpage( req = self._request_webpage(
redirect_req, video_id, redirect_req, video_id,
note='Resolving final URL', errnote='Could not resolve final URL') note='Resolving final URL', errnote='Could not resolve final URL')
video_url = req.geturl() video_url = req.url
if video_url.endswith('.html'): if video_url.endswith('.html'):
raise ExtractorError('Redirect failed') raise ExtractorError('Redirect failed')

View File

@ -6,7 +6,8 @@ import time
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str from ..compat import compat_str
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
@ -233,7 +234,7 @@ class HotStarIE(HotStarBaseIE):
'height': int_or_none(playback_set.get('height')), 'height': int_or_none(playback_set.get('height')),
}] }]
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
geo_restricted = True geo_restricted = True
continue continue

View File

@ -1,13 +1,13 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
parse_age_limit, parse_age_limit,
sanitized_Request,
try_get, try_get,
) )
@ -42,7 +42,7 @@ class HRTiBaseIE(InfoExtractor):
'application_version': self._APP_VERSION 'application_version': self._APP_VERSION
} }
req = sanitized_Request(self._API_URL, data=json.dumps(app_data).encode('utf-8')) req = Request(self._API_URL, data=json.dumps(app_data).encode('utf-8'))
req.get_method = lambda: 'PUT' req.get_method = lambda: 'PUT'
resources = self._download_json( resources = self._download_json(
@ -73,8 +73,8 @@ class HRTiBaseIE(InfoExtractor):
self._login_url, None, note='Logging in', errnote='Unable to log in', self._login_url, None, note='Logging in', errnote='Unable to log in',
data=json.dumps(auth_data).encode('utf-8')) data=json.dumps(auth_data).encode('utf-8'))
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 406: if isinstance(e.cause, HTTPError) and e.cause.status == 406:
auth_info = self._parse_json(e.cause.read().encode('utf-8'), None) auth_info = self._parse_json(e.cause.response.read().encode('utf-8'), None)
else: else:
raise raise

View File

@ -1,8 +1,9 @@
import re import re
import urllib.error import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_parse_qs from ..compat import compat_parse_qs
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
@ -27,9 +28,9 @@ class IGNBaseIE(InfoExtractor):
try: try:
return self._call_api(slug) return self._call_api(slug)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404: if isinstance(e.cause, HTTPError) and e.cause.status == 404:
e.cause.args = e.cause.args or [ e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason] e.cause.response.url, e.cause.status, e.cause.reason]
raise ExtractorError( raise ExtractorError(
'Content not found: expired?', cause=e.cause, 'Content not found: expired?', cause=e.cause,
expected=True) expected=True)
@ -226,7 +227,7 @@ class IGNVideoIE(IGNBaseIE):
parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed')) parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed'))
webpage, urlh = self._download_webpage_handle(embed_url, video_id) webpage, urlh = self._download_webpage_handle(embed_url, video_id)
new_url = urlh.geturl() new_url = urlh.url
ign_url = compat_parse_qs( ign_url = compat_parse_qs(
urllib.parse.urlparse(new_url).query).get('url', [None])[-1] urllib.parse.urlparse(new_url).query).get('url', [None])[-1]
if ign_url: if ign_url:
@ -323,14 +324,14 @@ class IGNArticleIE(IGNBaseIE):
try: try:
return self._call_api(slug) return self._call_api(slug)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError): if isinstance(e.cause, HTTPError):
e.cause.args = e.cause.args or [ e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason] e.cause.response.url, e.cause.status, e.cause.reason]
if e.cause.code == 404: if e.cause.status == 404:
raise ExtractorError( raise ExtractorError(
'Content not found: expired?', cause=e.cause, 'Content not found: expired?', cause=e.cause,
expected=True) expected=True)
elif e.cause.code == 503: elif e.cause.status == 503:
self.report_warning(error_to_compat_str(e.cause)) self.report_warning(error_to_compat_str(e.cause))
return return
raise raise

View File

@ -1,7 +1,7 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -52,9 +52,9 @@ class ImgGamingBaseIE(InfoExtractor):
return self._call_api( return self._call_api(
stream_path, media_id)['playerUrlCallback'] stream_path, media_id)['playerUrlCallback']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
raise ExtractorError( raise ExtractorError(
self._parse_json(e.cause.read().decode(), media_id)['messages'][0], self._parse_json(e.cause.response.read().decode(), media_id)['messages'][0],
expected=True) expected=True)
raise raise

View File

@ -3,9 +3,9 @@ import itertools
import json import json
import re import re
import time import time
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
decode_base_n, decode_base_n,
@ -442,7 +442,7 @@ class InstagramIE(InstagramBaseIE):
shared_data = self._search_json( shared_data = self._search_json(
r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) or {} r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) or {}
if shared_data and self._LOGIN_URL not in urlh.geturl(): if shared_data and self._LOGIN_URL not in urlh.url:
media.update(traverse_obj( media.update(traverse_obj(
shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'), shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'),
('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {}) ('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {})
@ -589,7 +589,7 @@ class InstagramPlaylistBaseIE(InstagramBaseIE):
except ExtractorError as e: except ExtractorError as e:
# if it's an error caused by a bad query, and there are # if it's an error caused by a bad query, and there are
# more GIS templates to try, ignore it and keep trying # more GIS templates to try, ignore it and keep trying
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
if gis_tmpl != gis_tmpls[-1]: if gis_tmpl != gis_tmpls[-1]:
continue continue
raise raise

View File

@ -81,7 +81,7 @@ class IPrimaIE(InfoExtractor):
note='Logging in') note='Logging in')
# a profile may need to be selected first, even when there is only a single one # a profile may need to be selected first, even when there is only a single one
if '/profile-select' in login_handle.geturl(): if '/profile-select' in login_handle.url:
profile_id = self._search_regex( profile_id = self._search_regex(
r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id') r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id')
@ -89,7 +89,7 @@ class IPrimaIE(InfoExtractor):
f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None, f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None,
query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile') query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile')
code = traverse_obj(login_handle.geturl(), ({parse_qs}, 'code', 0)) code = traverse_obj(login_handle.url, ({parse_qs}, 'code', 0))
if not code: if not code:
raise ExtractorError('Login failed', expected=True) raise ExtractorError('Login failed', expected=True)

View File

@ -1,5 +1,5 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -101,8 +101,8 @@ class KakaoIE(InfoExtractor):
cdn_api_base, video_id, query=query, cdn_api_base, video_id, query=query,
note='Downloading video URL for profile %s' % profile_name) note='Downloading video URL for profile %s' % profile_name)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
resp = self._parse_json(e.cause.read().decode(), video_id) resp = self._parse_json(e.cause.response.read().decode(), video_id)
if resp.get('code') == 'GeoBlocked': if resp.get('code') == 'GeoBlocked':
self.raise_geo_restricted() self.raise_geo_restricted()
raise raise

View File

@ -1,7 +1,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
HEADRequest,
UserNotLive, UserNotLive,
float_or_none, float_or_none,
merge_dicts, merge_dicts,

View File

@ -91,7 +91,7 @@ class KuwoIE(KuwoBaseIE):
webpage, urlh = self._download_webpage_handle( webpage, urlh = self._download_webpage_handle(
url, song_id, note='Download song detail info', url, song_id, note='Download song detail info',
errnote='Unable to get song detail info') errnote='Unable to get song detail info')
if song_id not in urlh.geturl() or '对不起,该歌曲由于版权问题已被下线,将返回网站首页' in webpage: if song_id not in urlh.url or '对不起,该歌曲由于版权问题已被下线,将返回网站首页' in webpage:
raise ExtractorError('this song has been offline because of copyright issues', expected=True) raise ExtractorError('this song has been offline because of copyright issues', expected=True)
song_name = self._html_search_regex( song_name = self._html_search_regex(

View File

@ -1,13 +1,8 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..networking import HEADRequest
float_or_none, from ..utils import float_or_none, int_or_none, parse_duration, unified_strdate
HEADRequest,
int_or_none,
parse_duration,
unified_strdate,
)
class LA7IE(InfoExtractor): class LA7IE(InfoExtractor):

View File

@ -3,9 +3,9 @@ import json
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
OnDemandPagedList, OnDemandPagedList,
UnsupportedError, UnsupportedError,
determine_ext, determine_ext,
@ -266,7 +266,7 @@ class LBRYIE(LBRYBaseIE):
# HEAD request returns redirect response to m3u8 URL if available # HEAD request returns redirect response to m3u8 URL if available
final_url = self._request_webpage( final_url = self._request_webpage(
HEADRequest(streaming_url), display_id, headers=headers, HEADRequest(streaming_url), display_id, headers=headers,
note='Downloading streaming redirect url info').geturl() note='Downloading streaming redirect url info').url
elif result.get('value_type') == 'stream': elif result.get('value_type') == 'stream':
claim_id, is_live = result['signing_channel']['claim_id'], True claim_id, is_live = result['signing_channel']['claim_id'], True

View File

@ -25,7 +25,7 @@ class LecturioBaseIE(InfoExtractor):
self._LOGIN_URL, None, 'Downloading login popup') self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(url_handle): def is_logged(url_handle):
return self._LOGIN_URL not in url_handle.geturl() return self._LOGIN_URL not in url_handle.url
# Already logged in # Already logged in
if is_logged(urlh): if is_logged(urlh):

View File

@ -1,7 +1,7 @@
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -75,7 +75,7 @@ class LEGOIE(InfoExtractor):
'videoId': '%s_%s' % (uuid.UUID(video_id), locale), 'videoId': '%s_%s' % (uuid.UUID(video_id), locale),
}, headers=self.geo_verification_headers()) }, headers=self.geo_verification_headers())
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451: if isinstance(e.cause, HTTPError) and e.cause.status == 451:
self.raise_geo_restricted(countries=countries) self.raise_geo_restricted(countries=countries)
raise raise

View File

@ -1,7 +1,7 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
float_or_none, float_or_none,
@ -69,8 +69,8 @@ class LimelightBaseIE(InfoExtractor):
item_id, 'Downloading PlaylistService %s JSON' % method, item_id, 'Downloading PlaylistService %s JSON' % method,
fatal=fatal, headers=headers) fatal=fatal, headers=headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] error = self._parse_json(e.cause.response.read().decode(), item_id)['detail']['contentAccessPermission']
if error == 'CountryDisabled': if error == 'CountryDisabled':
self.raise_geo_restricted() self.raise_geo_restricted()
raise ExtractorError(error, expected=True) raise ExtractorError(error, expected=True)

View File

@ -2,11 +2,8 @@ import json
import random import random
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_b64decode, compat_str
compat_b64decode, from ..networking.exceptions import HTTPError
compat_HTTPError,
compat_str,
)
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError, ExtractorError,
@ -107,7 +104,7 @@ class LinuxAcademyIE(InfoExtractor):
'sso': 'true', 'sso': 'true',
}) })
login_state_url = urlh.geturl() login_state_url = urlh.url
try: try:
login_page = self._download_webpage( login_page = self._download_webpage(
@ -119,8 +116,8 @@ class LinuxAcademyIE(InfoExtractor):
'Referer': login_state_url, 'Referer': login_state_url,
}) })
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
error = self._parse_json(e.cause.read(), None) error = self._parse_json(e.cause.response.read(), None)
message = error.get('description') or error['code'] message = error.get('description') or error['code']
raise ExtractorError( raise ExtractorError(
'%s said: %s' % (self.IE_NAME, message), expected=True) '%s said: %s' % (self.IE_NAME, message), expected=True)
@ -137,7 +134,7 @@ class LinuxAcademyIE(InfoExtractor):
}) })
access_token = self._search_regex( access_token = self._search_regex(
r'access_token=([^=&]+)', urlh.geturl(), r'access_token=([^=&]+)', urlh.url,
'access token', default=None) 'access token', default=None)
if not access_token: if not access_token:
access_token = self._parse_json( access_token = self._parse_json(

View File

@ -171,7 +171,7 @@ class MediasiteIE(InfoExtractor):
query = mobj.group('query') query = mobj.group('query')
webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer?
redirect_url = urlh.geturl() redirect_url = urlh.url
# XXX: might have also extracted UrlReferrer and QueryString from the html # XXX: might have also extracted UrlReferrer and QueryString from the html
service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex(

View File

@ -1,14 +1,14 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError,
clean_html, clean_html,
determine_ext, determine_ext,
ExtractorError,
extract_attributes, extract_attributes,
get_element_by_class, get_element_by_class,
get_element_html_by_id, get_element_html_by_id,
HEADRequest,
parse_qs, parse_qs,
unescapeHTML, unescapeHTML,
unified_timestamp, unified_timestamp,
@ -160,5 +160,5 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
canonical_url = self._request_webpage( canonical_url = self._request_webpage(
HEADRequest(canonical_url), video_id, HEADRequest(canonical_url), video_id,
note='Resolve canonical URL', note='Resolve canonical URL',
errnote='Could not resolve canonical URL').geturl() errnote='Could not resolve canonical URL').url
return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id) return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id)

View File

@ -1,9 +1,9 @@
import base64 import base64
import time import time
import urllib.error
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -86,8 +86,8 @@ class MGTVIE(InfoExtractor):
'type': 'pch5' 'type': 'pch5'
}, headers=self.geo_verification_headers())['data'] }, headers=self.geo_verification_headers())['data']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
error = self._parse_json(e.cause.read().decode(), None) error = self._parse_json(e.cause.response.read().decode(), None)
if error.get('code') == 40005: if error.get('code') == 40005:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES) self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
raise ExtractorError(error['msg'], expected=True) raise ExtractorError(error['msg'], expected=True)

View File

@ -106,7 +106,7 @@ class MindsIE(MindsBaseIE):
if poster: if poster:
urlh = self._request_webpage(poster, video_id, fatal=False) urlh = self._request_webpage(poster, video_id, fatal=False)
if urlh: if urlh:
thumbnail = urlh.geturl() thumbnail = urlh.url
return { return {
'id': video_id, 'id': video_id,

View File

@ -2,12 +2,8 @@ import random
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..networking import Request
xpath_text, from ..utils import ExtractorError, int_or_none, xpath_text
int_or_none,
ExtractorError,
sanitized_Request,
)
class MioMioIE(InfoExtractor): class MioMioIE(InfoExtractor):
@ -61,7 +57,7 @@ class MioMioIE(InfoExtractor):
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
video_id) video_id)
vid_config_request = sanitized_Request( vid_config_request = Request(
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
headers=http_headers) headers=http_headers)

View File

@ -2,16 +2,15 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..networking import HEADRequest, Request
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
RegexNotFoundError,
find_xpath_attr, find_xpath_attr,
fix_xml_ampersands, fix_xml_ampersands,
float_or_none, float_or_none,
HEADRequest,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
RegexNotFoundError,
sanitized_Request,
strip_or_none, strip_or_none,
timeconvert, timeconvert,
try_get, try_get,
@ -51,15 +50,15 @@ class MTVServicesInfoExtractor(InfoExtractor):
def _extract_mobile_video_formats(self, mtvn_id): def _extract_mobile_video_formats(self, mtvn_id):
webpage_url = self._MOBILE_TEMPLATE % mtvn_id webpage_url = self._MOBILE_TEMPLATE % mtvn_id
req = sanitized_Request(webpage_url) req = Request(webpage_url)
# Otherwise we get a webpage that would execute some javascript # Otherwise we get a webpage that would execute some javascript
req.add_header('User-Agent', 'curl/7') req.headers['User-Agent'] = 'curl/7'
webpage = self._download_webpage(req, mtvn_id, webpage = self._download_webpage(req, mtvn_id,
'Downloading mobile page') 'Downloading mobile page')
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url')) metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
req = HEADRequest(metrics_url) req = HEADRequest(metrics_url)
response = self._request_webpage(req, mtvn_id, 'Resolving url') response = self._request_webpage(req, mtvn_id, 'Resolving url')
url = response.geturl() url = response.url
# Transform the url to get the best quality: # Transform the url to get the best quality:
url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
return [{'url': url, 'ext': 'mp4'}] return [{'url': url, 'ext': 'mp4'}]

View File

@ -6,9 +6,9 @@ from .common import InfoExtractor
from .theplatform import ThePlatformIE, default_ns from .theplatform import ThePlatformIE, default_ns
from .adobepass import AdobePassIE from .adobepass import AdobePassIE
from ..compat import compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
RegexNotFoundError, RegexNotFoundError,
UserNotLive, UserNotLive,
clean_html, clean_html,

View File

@ -1,8 +1,8 @@
import itertools import itertools
import json import json
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError, make_archive_id, parse_iso8601, remove_start from ..utils import ExtractorError, make_archive_id, parse_iso8601, remove_start
_BASE_URL_RE = r'https?://(?:www\.|beta\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)' _BASE_URL_RE = r'https?://(?:www\.|beta\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
@ -48,7 +48,7 @@ class NebulaBaseIE(InfoExtractor):
return inner_call() return inner_call()
except ExtractorError as exc: except ExtractorError as exc:
# if 401 or 403, attempt credential re-auth and retry # if 401 or 403, attempt credential re-auth and retry
if exc.cause and isinstance(exc.cause, urllib.error.HTTPError) and exc.cause.code in (401, 403): if exc.cause and isinstance(exc.cause, HTTPError) and exc.cause.status in (401, 403):
self.to_screen(f'Reauthenticating to Nebula and retrying, because last {auth_type} call resulted in error {exc.cause.code}') self.to_screen(f'Reauthenticating to Nebula and retrying, because last {auth_type} call resulted in error {exc.cause.code}')
self._perform_login() self._perform_login()
return inner_call() return inner_call()

View File

@ -11,6 +11,7 @@ from random import randint
from .common import InfoExtractor from .common import InfoExtractor
from ..aes import aes_ecb_encrypt, pkcs7_padding from ..aes import aes_ecb_encrypt, pkcs7_padding
from ..compat import compat_urllib_parse_urlencode from ..compat import compat_urllib_parse_urlencode
from ..networking import Request
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
bytes_to_intlist, bytes_to_intlist,
@ -18,7 +19,6 @@ from ..utils import (
float_or_none, float_or_none,
int_or_none, int_or_none,
intlist_to_bytes, intlist_to_bytes,
sanitized_Request,
try_get, try_get,
) )
@ -146,8 +146,8 @@ class NetEaseMusicBaseIE(InfoExtractor):
return int(round(ms / 1000.0)) return int(round(ms / 1000.0))
def query_api(self, endpoint, video_id, note): def query_api(self, endpoint, video_id, note):
req = sanitized_Request('%s%s' % (self._API_BASE, endpoint)) req = Request('%s%s' % (self._API_BASE, endpoint))
req.add_header('Referer', self._API_BASE) req.headers['Referer'] = self._API_BASE
return self._download_json(req, video_id, note) return self._download_json(req, video_id, note)

View File

@ -8,10 +8,8 @@ import time
from urllib.parse import urlparse from urllib.parse import urlparse
from .common import InfoExtractor, SearchInfoExtractor from .common import InfoExtractor, SearchInfoExtractor
from ..compat import (
compat_HTTPError,
)
from ..dependencies import websockets from ..dependencies import websockets
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
OnDemandPagedList, OnDemandPagedList,
@ -396,7 +394,7 @@ class NiconicoIE(InfoExtractor):
webpage, handle = self._download_webpage_handle( webpage, handle = self._download_webpage_handle(
'https://www.nicovideo.jp/watch/' + video_id, video_id) 'https://www.nicovideo.jp/watch/' + video_id, video_id)
if video_id.startswith('so'): if video_id.startswith('so'):
video_id = self._match_id(handle.geturl()) video_id = self._match_id(handle.url)
api_data = self._parse_json(self._html_search_regex( api_data = self._parse_json(self._html_search_regex(
'data-api-data="([^"]+)"', webpage, 'data-api-data="([^"]+)"', webpage,
@ -407,9 +405,9 @@ class NiconicoIE(InfoExtractor):
'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id, round(time.time() * 1000)), video_id, 'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id, round(time.time() * 1000)), video_id,
note='Downloading API JSON', errnote='Unable to fetch data')['data'] note='Downloading API JSON', errnote='Unable to fetch data')['data']
except ExtractorError: except ExtractorError:
if not isinstance(e.cause, compat_HTTPError): if not isinstance(e.cause, HTTPError):
raise raise
webpage = e.cause.read().decode('utf-8', 'replace') webpage = e.cause.response.read().decode('utf-8', 'replace')
error_msg = self._html_search_regex( error_msg = self._html_search_regex(
r'(?s)<section\s+class="(?:(?:ErrorMessage|WatchExceptionPage-message)\s*)+">(.+?)</section>', r'(?s)<section\s+class="(?:(?:ErrorMessage|WatchExceptionPage-message)\s*)+">(.+?)</section>',
webpage, 'error reason', default=None) webpage, 'error reason', default=None)
@ -742,7 +740,7 @@ class NiconicoHistoryIE(NiconicoPlaylistBaseIE):
try: try:
mylist = self._call_api(list_id, 'list', {'pageSize': 1}) mylist = self._call_api(list_id, 'list', {'pageSize': 1})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
self.raise_login_required('You have to be logged in to get your history') self.raise_login_required('You have to be logged in to get your history')
raise raise
return self.playlist_result(self._entries(list_id), list_id, **self._parse_owner(mylist)) return self.playlist_result(self._entries(list_id), list_id, **self._parse_owner(mylist))
@ -951,8 +949,8 @@ class NiconicoLiveIE(InfoExtractor):
'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9', 'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9',
}) })
hostname = remove_start(urlparse(urlh.geturl()).hostname, 'sp.') hostname = remove_start(urlparse(urlh.url).hostname, 'sp.')
cookies = try_get(urlh.geturl(), self._downloader._calc_cookies) cookies = try_get(urlh.url, self._downloader._calc_cookies)
latency = try_get(self._configuration_arg('latency'), lambda x: x[0]) latency = try_get(self._configuration_arg('latency'), lambda x: x[0])
if latency not in self._KNOWN_LATENCY: if latency not in self._KNOWN_LATENCY:
latency = 'high' latency = 'high'

View File

@ -51,7 +51,7 @@ class NJPWWorldIE(InfoExtractor):
data=urlencode_postdata({'login_id': username, 'pw': password}), data=urlencode_postdata({'login_id': username, 'pw': password}),
headers={'Referer': 'https://front.njpwworld.com/auth'}) headers={'Referer': 'https://front.njpwworld.com/auth'})
# /auth/login will return 302 for successful logins # /auth/login will return 302 for successful logins
if urlh.geturl() == self._LOGIN_URL: if urlh.url == self._LOGIN_URL:
self.report_warning('unable to login') self.report_warning('unable to login')
return False return False

View File

@ -1,9 +1,9 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import Request
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
sanitized_Request,
urlencode_postdata, urlencode_postdata,
xpath_text, xpath_text,
xpath_with_ns, xpath_with_ns,
@ -36,8 +36,8 @@ class NosVideoIE(InfoExtractor):
'op': 'download1', 'op': 'download1',
'method_free': 'Continue to Video', 'method_free': 'Continue to Video',
} }
req = sanitized_Request(url, urlencode_postdata(fields)) req = Request(url, urlencode_postdata(fields))
req.add_header('Content-type', 'application/x-www-form-urlencoded') req.headers['Content-type'] = 'application/x-www-form-urlencoded'
webpage = self._download_webpage(req, video_id, webpage = self._download_webpage(req, video_id,
'Downloading download page') 'Downloading download page')
if re.search(self._FILE_DELETED_REGEX, webpage) is not None: if re.search(self._FILE_DELETED_REGEX, webpage) is not None:

View File

@ -4,10 +4,8 @@ from .brightcove import (
) )
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..networking import Request
ExtractorError, from ..utils import ExtractorError
sanitized_Request,
)
class NownessBaseIE(InfoExtractor): class NownessBaseIE(InfoExtractor):
@ -40,7 +38,7 @@ class NownessBaseIE(InfoExtractor):
def _api_request(self, url, request_path): def _api_request(self, url, request_path):
display_id = self._match_id(url) display_id = self._match_id(url)
request = sanitized_Request( request = Request(
'http://api.nowness.com/api/' + request_path % display_id, 'http://api.nowness.com/api/' + request_path % display_id,
headers={ headers={
'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us', 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',

View File

@ -3,7 +3,8 @@ import random
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str from ..compat import compat_str
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
@ -148,7 +149,7 @@ class NRKIE(NRKBaseIE):
try: try:
return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query) return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: if isinstance(e.cause, HTTPError) and e.cause.status == 400:
return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query) return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query)
raise raise

View File

@ -1,7 +1,7 @@
import json import json
import urllib.error
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
GeoRestrictedError, GeoRestrictedError,
@ -74,8 +74,8 @@ class OnDemandChinaEpisodeIE(InfoExtractor):
f'https://odkmedia.io/odc/api/v2/playback/{video_info["id"]}/', display_id, f'https://odkmedia.io/odc/api/v2/playback/{video_info["id"]}/', display_id,
headers={'Authorization': '', 'service-name': 'odc'}) headers={'Authorization': '', 'service-name': 'odc'})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError): if isinstance(e.cause, HTTPError):
error_data = self._parse_json(e.cause.read(), display_id)['detail'] error_data = self._parse_json(e.cause.response.read(), display_id)['detail']
raise GeoRestrictedError(error_data) raise GeoRestrictedError(error_data)
formats, subtitles = [], {} formats, subtitles = [], {}

View File

@ -7,9 +7,9 @@ from ..compat import (
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
) )
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
float_or_none, float_or_none,
int_or_none, int_or_none,
qualities, qualities,
@ -448,7 +448,7 @@ class OdnoklassnikiIE(InfoExtractor):
json_data = self._parse_json(unescapeHTML(json_data), video_id) or {} json_data = self._parse_json(unescapeHTML(json_data), video_id) or {}
redirect_url = self._request_webpage(HEADRequest( redirect_url = self._request_webpage(HEADRequest(
json_data['videoSrc']), video_id, 'Requesting download URL').geturl() json_data['videoSrc']), video_id, 'Requesting download URL').url
self._clear_cookies(redirect_url) self._clear_cookies(redirect_url)
return { return {

View File

@ -2,11 +2,11 @@ import functools
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
clean_html, clean_html,
determine_ext, determine_ext,
float_or_none, float_or_none,
HEADRequest,
InAdvancePagedList, InAdvancePagedList,
int_or_none, int_or_none,
join_nonempty, join_nonempty,

View File

@ -44,7 +44,7 @@ class OwnCloudIE(InfoExtractor):
webpage, urlh = self._download_webpage_handle(url, video_id) webpage, urlh = self._download_webpage_handle(url, video_id)
if re.search(r'<label[^>]+for="password"', webpage): if re.search(r'<label[^>]+for="password"', webpage):
webpage = self._verify_video_password(webpage, urlh.geturl(), video_id) webpage = self._verify_video_password(webpage, urlh.url, video_id)
hidden_inputs = self._hidden_inputs(webpage) hidden_inputs = self._hidden_inputs(webpage)
title = hidden_inputs.get('filename') title = hidden_inputs.get('filename')

View File

@ -1,10 +1,7 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..networking.exceptions import HTTPError
# compat_str,
compat_HTTPError,
)
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError, ExtractorError,
@ -54,8 +51,8 @@ class PacktPubIE(PacktPubBaseIE):
'password': password, 'password': password,
}).encode())['data']['access'] }).encode())['data']['access']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 404): if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401, 404):
message = self._parse_json(e.cause.read().decode(), None)['message'] message = self._parse_json(e.cause.response.read().decode(), None)['message']
raise ExtractorError(message, expected=True) raise ExtractorError(message, expected=True)
raise raise
@ -70,7 +67,7 @@ class PacktPubIE(PacktPubBaseIE):
'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id, 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id,
'Downloading JSON video', headers=headers)['data'] 'Downloading JSON video', headers=headers)['data']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: if isinstance(e.cause, HTTPError) and e.cause.status == 400:
self.raise_login_required('This video is locked') self.raise_login_required('This video is locked')
raise raise

View File

@ -1,10 +1,10 @@
import itertools import itertools
from urllib.error import HTTPError
from .common import InfoExtractor from .common import InfoExtractor
from .vimeo import VimeoIE from .vimeo import VimeoIE
from ..compat import compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
clean_html, clean_html,
determine_ext, determine_ext,
@ -37,9 +37,9 @@ class PatreonBaseIE(InfoExtractor):
item_id, note='Downloading API JSON' if not note else note, item_id, note='Downloading API JSON' if not note else note,
query=query, fatal=fatal, headers=headers) query=query, fatal=fatal, headers=headers)
except ExtractorError as e: except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or mimetype2ext(e.cause.headers.get('Content-Type')) != 'json': if not isinstance(e.cause, HTTPError) or mimetype2ext(e.cause.response.headers.get('Content-Type')) != 'json':
raise raise
err_json = self._parse_json(self._webpage_read_content(e.cause, None, item_id), item_id, fatal=False) err_json = self._parse_json(self._webpage_read_content(e.cause.response, None, item_id), item_id, fatal=False)
err_message = traverse_obj(err_json, ('errors', ..., 'detail'), get_all=False) err_message = traverse_obj(err_json, ('errors', ..., 'detail'), get_all=False)
if err_message: if err_message:
raise ExtractorError(f'Patreon said: {err_message}', expected=True) raise ExtractorError(f'Patreon said: {err_message}', expected=True)

View File

@ -3,7 +3,7 @@ import re
import urllib.parse import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
float_or_none, float_or_none,
@ -83,8 +83,8 @@ class PelotonIE(InfoExtractor):
}).encode(), }).encode(),
headers={'Content-Type': 'application/json', 'User-Agent': 'web'}) headers={'Content-Type': 'application/json', 'User-Agent': 'web'})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
json_string = self._webpage_read_content(e.cause, None, video_id) json_string = self._webpage_read_content(e.cause.response, None, video_id)
res = self._parse_json(json_string, video_id) res = self._parse_json(json_string, video_id)
raise ExtractorError(res['message'], expected=res['message'] == 'Login failed') raise ExtractorError(res['message'], expected=res['message'] == 'Login failed')
else: else:
@ -96,8 +96,8 @@ class PelotonIE(InfoExtractor):
'https://api.onepeloton.com/api/subscription/stream', video_id, note='Downloading token', 'https://api.onepeloton.com/api/subscription/stream', video_id, note='Downloading token',
data=json.dumps({}).encode(), headers={'Content-Type': 'application/json'}) data=json.dumps({}).encode(), headers={'Content-Type': 'application/json'})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
json_string = self._webpage_read_content(e.cause, None, video_id) json_string = self._webpage_read_content(e.cause.response, None, video_id)
res = self._parse_json(json_string, video_id) res = self._parse_json(json_string, video_id)
raise ExtractorError(res['message'], expected=res['message'] == 'Stream limit reached') raise ExtractorError(res['message'], expected=res['message'] == 'Stream limit reached')
else: else:
@ -109,7 +109,7 @@ class PelotonIE(InfoExtractor):
try: try:
self._start_session(video_id) self._start_session(video_id)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
self._login(video_id) self._login(video_id)
self._start_session(video_id) self._start_session(video_id)
else: else:

View File

@ -69,7 +69,7 @@ class PiaproIE(InfoExtractor):
if urlh is False: if urlh is False:
login_ok = False login_ok = False
else: else:
parts = compat_urlparse.urlparse(urlh.geturl()) parts = compat_urlparse.urlparse(urlh.url)
if parts.path != '/': if parts.path != '/':
login_ok = False login_ok = False
if not login_ok: if not login_ok:

View File

@ -78,7 +78,7 @@ class PladformIE(InfoExtractor):
expected=True) expected=True)
if not video: if not video:
targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').geturl() targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').url
if targetUrl == url: if targetUrl == url:
raise ExtractorError('Can\'t parse page') raise ExtractorError('Can\'t parse page')
return self.url_result(targetUrl) return self.url_result(targetUrl)

View File

@ -36,7 +36,7 @@ class PlatziBaseIE(InfoExtractor):
headers={'Referer': self._LOGIN_URL}) headers={'Referer': self._LOGIN_URL})
# login succeeded # login succeeded
if 'platzi.com/login' not in urlh.geturl(): if 'platzi.com/login' not in urlh.url:
return return
login_error = self._webpage_read_content( login_error = self._webpage_read_content(

View File

@ -1,13 +1,9 @@
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking import PUTRequest
from ..utils import ( from ..networking.exceptions import HTTPError
clean_html, from ..utils import ExtractorError, clean_html, int_or_none
ExtractorError,
int_or_none,
PUTRequest,
)
class PlayPlusTVIE(InfoExtractor): class PlayPlusTVIE(InfoExtractor):
@ -47,9 +43,9 @@ class PlayPlusTVIE(InfoExtractor):
try: try:
self._token = self._download_json(req, None)['token'] self._token = self._download_json(req, None)['token']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise ExtractorError(self._parse_json( raise ExtractorError(self._parse_json(
e.cause.read(), None)['errorMessage'], expected=True) e.cause.response.read(), None)['errorMessage'], expected=True)
raise raise
self._profile = self._call_api('Profiles')['list'][0]['_id'] self._profile = self._call_api('Profiles')['list'][0]['_id']

View File

@ -3,11 +3,12 @@ import itertools
import math import math
import operator import operator
import re import re
import urllib.request
from .common import InfoExtractor from .common import InfoExtractor
from .openload import PhantomJSwrapper from .openload import PhantomJSwrapper
from ..compat import compat_HTTPError, compat_str from ..compat import compat_str
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
NO_DEFAULT, NO_DEFAULT,
ExtractorError, ExtractorError,
@ -46,8 +47,8 @@ class PornHubBaseIE(InfoExtractor):
r'document\.cookie\s*=\s*["\']RNKEY=', r'document\.cookie\s*=\s*["\']RNKEY=',
r'document\.location\.reload\(true\)')): r'document\.location\.reload\(true\)')):
url_or_request = args[0] url_or_request = args[0]
url = (url_or_request.get_full_url() url = (url_or_request.url
if isinstance(url_or_request, urllib.request.Request) if isinstance(url_or_request, Request)
else url_or_request) else url_or_request)
phantom = PhantomJSwrapper(self, required_version='2.0') phantom = PhantomJSwrapper(self, required_version='2.0')
phantom.get(url, html=webpage) phantom.get(url, html=webpage)
@ -602,7 +603,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
base_url, item_id, note, query={'page': num}) base_url, item_id, note, query={'page': num})
def is_404(e): def is_404(e):
return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404 return isinstance(e.cause, HTTPError) and e.cause.status == 404
base_url = url base_url = url
has_page = page is not None has_page = page is not None

View File

@ -1,8 +1,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_str
compat_HTTPError, from ..networking.exceptions import HTTPError
compat_str,
)
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -72,7 +70,7 @@ class PuhuTVIE(InfoExtractor):
display_id, 'Downloading video JSON', display_id, 'Downloading video JSON',
headers=self.geo_verification_headers()) headers=self.geo_verification_headers())
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, HTTPError) and e.cause.status == 403:
self.raise_geo_restricted() self.raise_geo_restricted()
raise raise

View File

@ -41,7 +41,7 @@ class RadikoBaseIE(InfoExtractor):
'x-radiko-device': 'pc', 'x-radiko-device': 'pc',
'x-radiko-user': 'dummy_user', 'x-radiko-user': 'dummy_user',
}) })
auth1_header = auth1_handle.info() auth1_header = auth1_handle.headers
auth_token = auth1_header['X-Radiko-AuthToken'] auth_token = auth1_header['X-Radiko-AuthToken']
kl = int(auth1_header['X-Radiko-KeyLength']) kl = int(auth1_header['X-Radiko-KeyLength'])

View File

@ -1,5 +1,5 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
@ -74,8 +74,8 @@ class RadioCanadaIE(InfoExtractor):
return self._download_json( return self._download_json(
'https://services.radio-canada.ca/media/' + path, video_id, query=query) 'https://services.radio-canada.ca/media/' + path, video_id, query=query)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422): if isinstance(e.cause, HTTPError) and e.cause.status in (401, 422):
data = self._parse_json(e.cause.read().decode(), None) data = self._parse_json(e.cause.response.read().decode(), None)
error = data.get('error_description') or data['errorMessage']['text'] error = data.get('error_description') or data['errorMessage']['text']
raise ExtractorError(error, expected=True) raise ExtractorError(error, expected=True)
raise raise

View File

@ -1,9 +1,9 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest,
base_url, base_url,
clean_html, clean_html,
extract_attributes, extract_attributes,

Some files were not shown because too many files have changed in this diff Show More