Mirrors
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[pornhub] Extract video URL from tv platform site (#12007, #12129)

This commit is contained in:
Sergey M․ 2017-02-14 23:52:41 +07:00
parent 5cb2d36c82
commit 9a372f14b4
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 30 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
youtube_dl/extractor/pornhub.py
View File

@ -2,27 +2,27 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools import itertools
import os # import os
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_HTTPError, compat_HTTPError,
compat_urllib_parse_unquote, # compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus, # compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlparse, # compat_urllib_parse_urlparse,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json, js_to_json,
orderedSet, orderedSet,
sanitized_Request, # sanitized_Request,
str_to_int, str_to_int,
) )
from ..aes import ( # from ..aes import (
aes_decrypt_text # aes_decrypt_text
) # )
class PornHubIE(InfoExtractor): class PornHubIE(InfoExtractor):
@ -109,10 +109,14 @@ class PornHubIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
req = sanitized_Request( def dl_webpage(platform):
'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) return self._download_webpage(
req.add_header('Cookie', 'age_verified=1') 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
webpage = self._download_webpage(req, video_id) video_id, headers={
'Cookie': 'age_verified=1; platform=%s' % platform,
})
webpage = dl_webpage('pc')
error_msg = self._html_search_regex( error_msg = self._html_search_regex(
r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>', r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
@ -123,10 +127,19 @@ class PornHubIE(InfoExtractor):
'PornHub said: %s' % error_msg, 'PornHub said: %s' % error_msg,
expected=True, video_id=video_id) expected=True, video_id=video_id)
tv_webpage = dl_webpage('tv')
video_url = self._search_regex(
r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
'video url', group='url')
title = self._search_regex(
r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
# video_title from flashvars contains whitespace instead of non-ASCII (see # video_title from flashvars contains whitespace instead of non-ASCII (see
# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
# on that anymore. # on that anymore.
title = self._html_search_meta( title = title or self._html_search_meta(
'twitter:title', webpage, default=None) or self._search_regex( 'twitter:title', webpage, default=None) or self._search_regex(
(r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
@ -156,6 +169,7 @@ class PornHubIE(InfoExtractor):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
"""
video_variables = {} video_variables = {}
for video_variablename, quote, video_variable in re.findall( for video_variablename, quote, video_variable in re.findall(
r'(player_quality_[0-9]{3,4}p\w+)\s*=\s*(["\'])(.+?)\2;', webpage): r'(player_quality_[0-9]{3,4}p\w+)\s*=\s*(["\'])(.+?)\2;', webpage):
@ -197,6 +211,7 @@ class PornHubIE(InfoExtractor):
'height': height, 'height': height,
}) })
self._sort_formats(formats) self._sort_formats(formats)
"""
page_params = self._parse_json(self._search_regex( page_params = self._parse_json(self._search_regex(
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
@ -209,6 +224,7 @@ class PornHubIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'uploader': video_uploader, 'uploader': video_uploader,
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
@ -217,7 +233,7 @@ class PornHubIE(InfoExtractor):
'like_count': like_count, 'like_count': like_count,
'dislike_count': dislike_count, 'dislike_count': dislike_count,
'comment_count': comment_count, 'comment_count': comment_count,
'formats': formats, # 'formats': formats,
'age_limit': 18, 'age_limit': 18,
'tags': tags, 'tags': tags,
'categories': categories, 'categories': categories,