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