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     lowercase_escape,
  10 )
  11
  12
  13 class GoogleDriveIE(InfoExtractor):
  14     _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     _TESTS = [{
  16         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
  17         'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
  18         'info_dict': {
  19             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
  20             'ext': 'mp4',
  21             'title': 'Big Buck Bunny.mp4',
  22             'duration': 45,
  23         }
  24     }, {
  25         # video id is longer than 28 characters
  26         'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
  27         'only_matching': True,
  28     }]
  29     _FORMATS_EXT = {
  30         '5': 'flv',
  31         '6': 'flv',
  32         '13': '3gp',
  33         '17': '3gp',
  34         '18': 'mp4',
  35         '22': 'mp4',
  36         '34': 'flv',
  37         '35': 'flv',
  38         '36': '3gp',
  39         '37': 'mp4',
  40         '38': 'mp4',
  41         '43': 'webm',
  42         '44': 'webm',
  43         '45': 'webm',
  44         '46': 'webm',
  45         '59': 'mp4',
  46     }
  47
  48     @staticmethod
  49     def _extract_url(webpage):
  50         mobj = re.search(
  51             r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
  52             webpage)
  53         if mobj:
  54             return 'https://drive.google.com/file/d/%s' % mobj.group('id')
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         webpage = self._download_webpage(
  59             'http://docs.google.com/file/d/%s' % video_id, video_id)
  60
  61         reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
  62         if reason:
  63             raise ExtractorError(reason)
  64
  65         title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
  66         duration = int_or_none(self._search_regex(
  67             r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
  68         fmt_stream_map = self._search_regex(
  69             r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
  70         fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
  71
  72         formats = []
  73         for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
  74             fmt_id, fmt_url = fmt_stream.split('|')
  75             resolution = fmt.split('/')[1]
  76             width, height = resolution.split('x')
  77             formats.append({
  78                 'url': lowercase_escape(fmt_url),
  79                 'format_id': fmt_id,
  80                 'resolution': resolution,
  81                 'width': int_or_none(width),
  82                 'height': int_or_none(height),
  83                 'ext': self._FORMATS_EXT[fmt_id],
  84             })
  85         self._sort_formats(formats)
  86
  87         return {
  88             'id': video_id,
  89             'title': title,
  90             'thumbnail': self._og_search_thumbnail(webpage, default=None),
  91             'duration': duration,
  92             'formats': formats,
  93         }