diff options
Diffstat (limited to 'youtube_dl/extractor/archiveorg.py')
| -rw-r--r-- | youtube_dl/extractor/archiveorg.py | 106 |
1 files changed, 67 insertions, 39 deletions
diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 8feb7cb74..e42ed5e79 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -1,67 +1,95 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + clean_html, + extract_attributes, + unified_strdate, + unified_timestamp, +) class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' + _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'md5': '8af1d4cf447933ed3c7f4871162602db', 'info_dict': { 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect', - 'ext': 'ogv', + 'ext': 'ogg', 'title': '1968 Demo - FJCC Conference Presentation Reel #1', - 'description': 'md5:1780b464abaca9991d8968c877bb53ed', - 'upload_date': '19681210', - 'uploader': 'SRI International' + 'description': 'md5:da45c349df039f1cc8075268eb1b5c25', + 'creator': 'SRI International', + 'release_date': '19681210', + 'uploader': 'SRI International', + 'timestamp': 1268695290, + 'upload_date': '20100315', } }, { 'url': 'https://archive.org/details/Cops1922', - 'md5': '18f2a19e6d89af8425671da1cf3d4e04', + 'md5': '0869000b4ce265e8ca62738b336b268a', 'info_dict': { 'id': 'Cops1922', - 'ext': 'ogv', + 'ext': 'mp4', 'title': 'Buster Keaton\'s "Cops" (1922)', - 'description': 'md5:70f72ee70882f713d4578725461ffcc3', + 'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c', + 'timestamp': 1387699629, + 'upload_date': '20131222', } + }, { + 'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect', + 'only_matching': True, + }, { + 'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://archive.org/embed/' + video_id, video_id) - json_url = url + ('&' if '?' in url else '?') + 'output=json' - data = self._download_json(json_url, video_id) - - def get_optional(data_dict, field): - return data_dict['metadata'].get(field, [None])[0] + playlist = None + play8 = self._search_regex( + r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage, + 'playlist', default=None) + if play8: + attrs = extract_attributes(play8) + playlist = attrs.get('value') + if not playlist: + # Old jwplayer fallback + playlist = self._search_regex( + r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)", + webpage, 'jwplayer playlist', default='[]') + jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False) + if jwplayer_playlist: + info = self._parse_jwplayer_data( + {'playlist': jwplayer_playlist}, video_id, base_url=url) + else: + # HTML5 media fallback + info = self._parse_html5_media_entries(url, webpage, video_id)[0] + info['id'] = video_id - title = get_optional(data, 'title') - description = get_optional(data, 'description') - uploader = get_optional(data, 'creator') - upload_date = unified_strdate(get_optional(data, 'date')) + def get_optional(metadata, field): + return metadata.get(field, [None])[0] - formats = [ - { - 'format': fdata['format'], - 'url': 'http://' + data['server'] + data['dir'] + fn, - 'file_size': int(fdata['size']), - } - for fn, fdata in data['files'].items() - if 'Video' in fdata['format']] - - self._sort_formats(formats) - - return { - '_type': 'video', - 'id': video_id, - 'title': title, - 'formats': formats, - 'description': description, - 'uploader': uploader, - 'upload_date': upload_date, - 'thumbnail': data.get('misc', {}).get('image'), - } + metadata = self._download_json( + 'http://archive.org/details/' + video_id, video_id, query={ + 'output': 'json', + })['metadata'] + info.update({ + 'title': get_optional(metadata, 'title') or info.get('title'), + 'description': clean_html(get_optional(metadata, 'description')), + }) + if info.get('_type') != 'playlist': + creator = get_optional(metadata, 'creator') + info.update({ + 'creator': creator, + 'release_date': unified_strdate(get_optional(metadata, 'date')), + 'uploader': get_optional(metadata, 'publisher') or creator, + 'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')), + 'language': get_optional(metadata, 'language'), + }) + return info |