youtube_dl/extractor/dropbox.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import os.path
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_urllib_parse_unquote
   9 from ..utils import url_basename
  10
  11
  12 class DropboxIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
  14     _TESTS = [
  15         {
  16             'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
  17             'info_dict': {
  18                 'id': 'nelirfsxnmcfbfh',
  19                 'ext': 'mp4',
  20                 'title': 'youtube-dl test video \'ä"BaW_jenozKc'
  21             }
  22         }, {
  23             'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
  24             'only_matching': True,
  25         },
  26     ]
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31         fn = compat_urllib_parse_unquote(url_basename(url))
  32         title = os.path.splitext(fn)[0]
  33         video_url = re.sub(r'[?&]dl=0', '', url)
  34         video_url += ('?' if '?' not in video_url else '&') + 'dl=1'
  35
  36         return {
  37             'id': video_id,
  38             'title': title,
  39             'url': video_url,
  40         }