Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/extremetube.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_request
   7 from ..utils import (
   8     int_or_none,
   9     str_to_int,
  10 )
  11
  12
  13 class ExtremeTubeIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
  15     _TESTS = [{
  16         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  17         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
  18         'info_dict': {
  19             'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  20             'ext': 'mp4',
  21             'title': 'Music Video 14 british euro brit european cumshots swallow',
  22             'uploader': 'unknown',
  23             'view_count': int,
  24             'age_limit': 18,
  25         }
  26     }, {
  27         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  28         'only_matching': True,
  29     }, {
  30         'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
  31         'only_matching': True,
  32     }, {
  33         'url': 'http://www.extremetube.com/video/652431',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         req = compat_urllib_request.Request(url)
  41         req.add_header('Cookie', 'age_verified=1')
  42         webpage = self._download_webpage(req, video_id)
  43
  44         video_title = self._html_search_regex(
  45             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  46         uploader = self._html_search_regex(
  47             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
  48             webpage, 'uploader', fatal=False)
  49         view_count = str_to_int(self._html_search_regex(
  50             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
  51             webpage, 'view count', fatal=False))
  52
  53         flash_vars = self._parse_json(
  54             self._search_regex(
  55                 r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
  56             video_id)
  57
  58         formats = []
  59         for quality_key, video_url in flash_vars.items():
  60             height = int_or_none(self._search_regex(
  61                 r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
  62             if not height:
  63                 continue
  64             f = {
  65                 'url': video_url,
  66             }
  67             mobj = re.search(
  68                 r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
  69             if mobj:
  70                 height = int(mobj.group('height'))
  71                 bitrate = int(mobj.group('bitrate'))
  72                 f.update({
  73                     'format_id': '%dp-%dk' % (height, bitrate),
  74                     'height': height,
  75                     'tbr': bitrate,
  76                 })
  77             else:
  78                 f.update({
  79                     'format_id': '%dp' % height,
  80                     'height': height,
  81                 })
  82             formats.append(f)
  83         self._sort_formats(formats)
  84
  85         return {
  86             'id': video_id,
  87             'title': video_title,
  88             'formats': formats,
  89             'uploader': uploader,
  90             'view_count': view_count,
  91             'age_limit': 18,
  92         }