1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class GoogleDriveIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
15 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
16 'md5': '881f7700aec4f538571fa1e0eed4a7b6',
18 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
20 'title': 'Big Buck Bunny.mp4',
44 def _extract_url(webpage):
46 r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
49 return 'https://drive.google.com/file/d/%s' % mobj.group('id')
51 def _real_extract(self, url):
52 video_id = self._match_id(url)
53 webpage = self._download_webpage(
54 'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
56 reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
58 raise ExtractorError(reason)
60 title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
61 duration = int_or_none(self._search_regex(
62 r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
63 fmt_stream_map = self._search_regex(
64 r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
65 fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
68 for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
69 fmt_id, fmt_url = fmt_stream.split('|')
70 resolution = fmt.split('/')[1]
71 width, height = resolution.split('x')
75 'resolution': resolution,
76 'width': int_or_none(width),
77 'height': int_or_none(height),
78 'ext': self._FORMATS_EXT[fmt_id],
80 self._sort_formats(formats)
85 'thumbnail': self._og_search_thumbnail(webpage),