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