From e251986cbe7c62a7bef02a1a32bae21dff25565e Mon Sep 17 00:00:00 2001 From: Eren Kemer Date: Mon, 8 Aug 2022 23:09:37 +0200 Subject: [PATCH] [extractor/harpodeon] Add extractor (#4540) Closes #4450 Authored by: eren-kemer --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/harpodeon.py | 70 +++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) create mode 100644 yt_dlp/extractor/harpodeon.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 3abae19b0..0bb685fa2 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -631,6 +631,7 @@ from .gronkh import ( GronkhVodsIE ) from .groupon import GrouponIE +from .harpodeon import HarpodeonIE from .hbo import HBOIE from .hearthisat import HearThisAtIE from .heise import HeiseIE diff --git a/yt_dlp/extractor/harpodeon.py b/yt_dlp/extractor/harpodeon.py new file mode 100644 index 000000000..0aa47337f --- /dev/null +++ b/yt_dlp/extractor/harpodeon.py @@ -0,0 +1,70 @@ +from .common import InfoExtractor +from ..utils import unified_strdate + + +class HarpodeonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?harpodeon\.com/(?:video|preview)/\w+/(?P\d+)' + _TESTS = [{ + 'url': 'https://www.harpodeon.com/video/The_Smoking_Out_of_Bella_Butts/268068288', + 'md5': '727371564a6a9ebccef2073535b5b6bd', + 'skip': 'Free video could become unavailable', + 'info_dict': { + 'id': '268068288', + 'ext': 'mp4', + 'title': 'The Smoking Out of Bella Butts', + 'description': 'md5:47e16bdb41fc8a79c83ab83af11c8b77', + 'creator': 'Vitagraph Company of America', + 'release_date': '19150101' + } + }, { + 'url': 'https://www.harpodeon.com/preview/The_Smoking_Out_of_Bella_Butts/268068288', + 'md5': '6dfea5412845f690c7331be703f884db', + 'info_dict': { + 'id': '268068288', + 'ext': 'mp4', + 'title': 'The Smoking Out of Bella Butts', + 'description': 'md5:47e16bdb41fc8a79c83ab83af11c8b77', + 'creator': 'Vitagraph Company of America', + 'release_date': '19150101' + } + }, { + 'url': 'https://www.harpodeon.com/preview/Behind_the_Screen/421838710', + 'md5': '7979df9ca04637282cb7d172ab3a9c3b', + 'info_dict': { + 'id': '421838710', + 'ext': 'mp4', + 'title': 'Behind the Screen', + 'description': 'md5:008972a3dc51fba3965ee517d2ba9155', + 'creator': 'Lone Star Corporation', + 'release_date': '19160101' + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title, creator, release_year = self._search_regex( + r'''(?x) + ]+videoInfo[^<]*]*>(?P[^>]+)</h2> + (?:\s*<p[^>]*>\((?P<creator>.+),\s*)?(?P<release_year>\d{4})?''', + webpage, 'title', group=('title', 'creator', 'release_year'), + fatal=False) or (None, None, None) + + hp_base = self._html_search_regex(r'hpBase\(\s*["\']([^"\']+)', webpage, 'hp_base') + + hp_inject_video, hp_resolution = self._search_regex( + r'''(?x) + hpInjectVideo\([\'\"](?P<hp_inject_video>\w+)[\'\"], + [\'\"](?P<hp_resolution>\d+)[\'\"]''', + webpage, 'hp_inject_video', group=['hp_inject_video', 'hp_resolution']) + + return { + 'id': video_id, + 'title': title, + 'url': f'{hp_base}{hp_inject_video}_{hp_resolution}.mp4', + 'http_headers': {'Referer': url}, + 'description': self._html_search_meta('description', webpage, fatal=False), + 'creator': creator, + 'release_date': unified_strdate(f'{release_year}0101') + }