_ Git - youtube-dl/blob - youtube_dl/extractor/sharesix.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     parse_duration,
  13 )
  14
  15
  16 class ShareSixIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)'
  18     _TESTS = [
  19         {
  20             'url': 'http://sharesix.com/f/OXjQ7Y6',
  21             'md5': '9e8e95d8823942815a7d7c773110cc93',
  22             'info_dict': {
  23                 'id': 'OXjQ7Y6',
  24                 'ext': 'mp4',
  25                 'title': 'big_buck_bunny_480p_surround-fix.avi',
  26                 'duration': 596,
  27                 'width': 854,
  28                 'height': 480,
  29             },
  30         },
  31         {
  32             'url': 'http://sharesix.com/lfrwoxp35zdd',
  33             'md5': 'dd19f1435b7cec2d7912c64beeee8185',
  34             'info_dict': {
  35                 'id': 'lfrwoxp35zdd',
  36                 'ext': 'flv',
  37                 'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv',
  38                 'duration': 65,
  39                 'width': 1280,
  40                 'height': 720,
  41             },
  42         }
  43     ]
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_id = mobj.group('id')
  48
  49         fields = {
  50             'method_free': 'Free'
  51         }
  52         post = compat_urllib_parse.urlencode(fields)
  53         req = compat_urllib_request.Request(url, post)
  54         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  55
  56         webpage = self._download_webpage(req, video_id,
  57                                          'Downloading video page')
  58
  59         video_url = self._search_regex(
  60             r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL')
  61         title = self._html_search_regex(
  62             r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title')
  63         duration = parse_duration(
  64             self._search_regex(
  65                 r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>',
  66                 webpage,
  67                 'duration',
  68                 fatal=False
  69             )
  70         )
  71
  72         m = re.search(
  73             r'''(?xs)<dt>Width\sx\sHeight</dt>.+?
  74                      <dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''',
  75             webpage
  76         )
  77         width = height = None
  78         if m:
  79             width, height = int(m.group('width')), int(m.group('height'))
  80
  81         formats = [{
  82             'format_id': 'sd',
  83             'url': video_url,
  84             'width': width,
  85             'height': height,
  86         }]
  87
  88         return {
  89             'id': video_id,
  90             'title': title,
  91             'duration': duration,
  92             'formats': formats,
  93         }