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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     parse_duration,
   9     qualities,
  10     unified_strdate,
  11 )
  12
  13
  14 class CCCIE(InfoExtractor):
  15     IE_NAME = 'media.ccc.de'
  16     _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
  17
  18     _TESTS = [{
  19         'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
  20         'md5': '3a1eda8f3a29515d27f5adb967d7e740',
  21         'info_dict': {
  22             'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
  23             'ext': 'mp4',
  24             'title': 'Introduction to Processor Design',
  25             'description': 'md5:80be298773966f66d56cb11260b879af',
  26             'thumbnail': 're:^https?://.*\.jpg$',
  27             'view_count': int,
  28             'upload_date': '20131228',
  29             'duration': 3660,
  30         }
  31     }, {
  32         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(url, video_id)
  39
  40         if self._downloader.params.get('prefer_free_formats'):
  41             preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
  42         else:
  43             preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
  44
  45         title = self._html_search_regex(
  46             r'(?s)<h1>(.*?)</h1>', webpage, 'title')
  47         description = self._html_search_regex(
  48             r'(?s)<h3>About</h3>(.+?)<h3>',
  49             webpage, 'description', fatal=False)
  50         upload_date = unified_strdate(self._html_search_regex(
  51             r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",
  52             webpage, 'upload date', fatal=False))
  53         view_count = int_or_none(self._html_search_regex(
  54             r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
  55             webpage, 'view count', fatal=False))
  56         duration = parse_duration(self._html_search_regex(
  57             r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
  58             webpage, 'duration', fatal=False, group='duration'))
  59
  60         matches = re.finditer(r'''(?xs)
  61             <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
  62             <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
  63             <a\s+download\s+href='(?P<http_url>[^']+)'>\s*
  64             (?:
  65                 .*?
  66                 <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
  67             )?''', webpage)
  68         formats = []
  69         for m in matches:
  70             format = m.group('format')
  71             format_id = self._search_regex(
  72                 r'.*/([a-z0-9_-]+)/[^/]*$',
  73                 m.group('http_url'), 'format id', default=None)
  74             if format_id:
  75                 format_id = m.group('lang') + '-' + format_id
  76             vcodec = 'h264' if 'h264' in format_id else (
  77                 'none' if format_id in ('mp3', 'opus') else None
  78             )
  79             formats.append({
  80                 'format_id': format_id,
  81                 'format': format,
  82                 'language': m.group('lang'),
  83                 'url': m.group('http_url'),
  84                 'vcodec': vcodec,
  85                 'preference': preference(format_id),
  86             })
  87
  88             if m.group('torrent_url'):
  89                 formats.append({
  90                     'format_id': 'torrent-%s' % (format if format_id is None else format_id),
  91                     'format': '%s (torrent)' % format,
  92                     'proto': 'torrent',
  93                     'format_note': '(unsupported; will just download the .torrent file)',
  94                     'vcodec': vcodec,
  95                     'preference': -100 + preference(format_id),
  96                     'url': m.group('torrent_url'),
  97                 })
  98         self._sort_formats(formats)
  99
 100         thumbnail = self._html_search_regex(
 101             r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
 102
 103         return {
 104             'id': video_id,
 105             'title': title,
 106             'description': description,
 107             'thumbnail': thumbnail,
 108             'view_count': view_count,
 109             'upload_date': upload_date,
 110             'duration': duration,
 111             'formats': formats,
 112         }