youtube_dl/extractor/googledrive.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9 )
  10
  11
  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,})'
  14     _TESTS = [{
  15         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
  16         'md5': '881f7700aec4f538571fa1e0eed4a7b6',
  17         'info_dict': {
  18             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
  19             'ext': 'mp4',
  20             'title': 'Big Buck Bunny.mp4',
  21             'duration': 46,
  22         }
  23     }, {
  24         # video id is longer than 28 characters
  25         'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
  26         'only_matching': True,
  27     }]
  28     _FORMATS_EXT = {
  29         '5': 'flv',
  30         '6': 'flv',
  31         '13': '3gp',
  32         '17': '3gp',
  33         '18': 'mp4',
  34         '22': 'mp4',
  35         '34': 'flv',
  36         '35': 'flv',
  37         '36': '3gp',
  38         '37': 'mp4',
  39         '38': 'mp4',
  40         '43': 'webm',
  41         '44': 'webm',
  42         '45': 'webm',
  43         '46': 'webm',
  44         '59': 'mp4',
  45     }
  46
  47     @staticmethod
  48     def _extract_url(webpage):
  49         mobj = re.search(
  50             r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
  51             webpage)
  52         if mobj:
  53             return 'https://drive.google.com/file/d/%s' % mobj.group('id')
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57         webpage = self._download_webpage(
  58             'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
  59
  60         reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
  61         if reason:
  62             raise ExtractorError(reason)
  63
  64         title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
  65         duration = int_or_none(self._search_regex(
  66             r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
  67         fmt_stream_map = self._search_regex(
  68             r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
  69         fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
  70
  71         formats = []
  72         for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
  73             fmt_id, fmt_url = fmt_stream.split('|')
  74             resolution = fmt.split('/')[1]
  75             width, height = resolution.split('x')
  76             formats.append({
  77                 'url': fmt_url,
  78                 'format_id': fmt_id,
  79                 'resolution': resolution,
  80                 'width': int_or_none(width),
  81                 'height': int_or_none(height),
  82                 'ext': self._FORMATS_EXT[fmt_id],
  83             })
  84         self._sort_formats(formats)
  85
  86         return {
  87             'id': video_id,
  88             'title': title,
  89             'thumbnail': self._og_search_thumbnail(webpage, default=None),
  90             'duration': duration,
  91             'formats': formats,
  92         }