From fec040e7549d06e91dae31da53bee855630d0adf Mon Sep 17 00:00:00 2001 From: remitamine Date: Thu, 31 Dec 2015 17:29:37 +0100 Subject: [PATCH] [discovery] add support for discovery related sites - investigationdiscovery.com - discoverylife.com - animalplanet.com - ahctv.com - destinationamerica.com - sciencechannel.com - tlc.com - velocity.com --- youtube_dl/extractor/__init__.py | 1 - youtube_dl/extractor/animalplanet.py | 53 ---------------------------- youtube_dl/extractor/discovery.py | 39 +++++++++++++++----- 3 files changed, 30 insertions(+), 63 deletions(-) delete mode 100644 youtube_dl/extractor/animalplanet.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 732229c14..bae151e58 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -19,7 +19,6 @@ from .aftonbladet import AftonbladetIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE -from .animalplanet import AnimalPlanetIE from .anitube import AnitubeIE from .anysex import AnySexIE from .aol import AolIE diff --git a/youtube_dl/extractor/animalplanet.py b/youtube_dl/extractor/animalplanet.py deleted file mode 100644 index 0cebc8185..000000000 --- a/youtube_dl/extractor/animalplanet.py +++ /dev/null @@ -1,53 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - parse_duration, - parse_iso8601, -) - - -class AnimalPlanetIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/([^/]+/)*(?P[^/\?#]+)' - _TESTS = [{ - 'url': 'http://www.animalplanet.com/tv-shows/i-shouldnt-be-alive/videos/dog-saves-injured-owner/', - 'info_dict': { - 'id': '10608', - 'ext': 'mp4', - 'title': 'Dog Saves Injured Owner', - 'description': 'A world class athlete is put to the test when she falls into a canyon and breaks her hip. Her only companion is her dog, Taz, who is on a mission to save her!', - 'upload_date': '20100410', - 'timestamp': 1270857727, - 'duration': 220, - }, - 'params': { - # m3u8 download - 'skip_download': True, - } - }, { - 'url': 'http://www.animalplanet.com/longfin-eels-maneaters/', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - video_data = self._parse_json(self._search_regex( - r'initialVideoData\s*=\s*({.+?});', - webpage, 'initialVideoData'), display_id)['playlist'][0] - - return { - 'id': compat_str(video_data['id']), - 'display_id': display_id, - 'title': video_data['title'], - 'description': video_data.get('description'), - 'thumbnail': video_data.get('thumbnailURL'), - 'duration': parse_duration(video_data.get('video_length')), - 'timestamp': parse_iso8601(video_data.get('publishedDate')), - 'formats': self._extract_m3u8_formats( - video_data['src'], display_id, 'mp4', - 'm3u8_native', m3u8_id='hls') - } diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 507f4bdad..2626d85e3 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -9,7 +9,17 @@ from ..compat import compat_str class DiscoveryIE(InfoExtractor): - _VALID_URL = r'https?://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P[a-zA-Z0-9_\-]*)(?:\.htm)?' + _VALID_URL = r'''(?x)http://(?:www\.)?(?: + discovery| + investigationdiscovery| + discoverylife| + animalplanet| + ahctv| + destinationamerica| + sciencechannel| + tlc| + velocity + )\.com/([^/]+/)*(?P[^\./\?#]+)''' _TESTS = [{ 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', 'info_dict': { @@ -21,8 +31,8 @@ class DiscoveryIE(InfoExtractor): 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' ' back.'), 'duration': 156, - 'timestamp': 1303099200, - 'upload_date': '20110418', + 'timestamp': 1302032462, + 'upload_date': '20110405', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -33,27 +43,38 @@ class DiscoveryIE(InfoExtractor): 'id': 'mythbusters-the-simpsons', 'title': 'MythBusters: The Simpsons', }, - 'playlist_count': 9, + 'playlist_mincount': 10, + }, { + 'url': 'http://www.animalplanet.com/longfin-eels-maneaters/', + 'info_dict': { + 'id': '78326', + 'ext': 'mp4', + 'title': 'Longfin Eels: Maneaters?', + 'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.', + 'upload_date': '20140725', + 'timestamp': 1406246400, + 'duration': 116, + }, }] def _real_extract(self, url): - video_id = self._match_id(url) - info = self._download_json(url + '?flat=1', video_id) + display_id = self._match_id(url) + info = self._download_json(url + '?flat=1', display_id) video_title = info.get('playlist_title') or info.get('video_title') entries = [{ 'id': compat_str(video_info['id']), 'formats': self._extract_m3u8_formats( - video_info['src'], video_id, ext='mp4', + video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls', note='Download m3u8 information for video %d' % (idx + 1)), 'title': video_info['title'], 'description': video_info.get('description'), 'duration': parse_duration(video_info.get('video_length')), - 'webpage_url': video_info.get('href'), + 'webpage_url': video_info.get('href') or video_info.get('url'), 'thumbnail': video_info.get('thumbnailURL'), 'alt_title': video_info.get('secondary_title'), 'timestamp': parse_iso8601(video_info.get('publishedDate')), } for idx, video_info in enumerate(info['playlist'])] - return self.playlist_result(entries, video_id, video_title) + return self.playlist_result(entries, display_id, video_title) -- 2.40.0