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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     determine_ext,
   9     int_or_none,
  10     js_to_json,
  11     mimetype2ext,
  12     parse_filesize,
  13 )
  14
  15
  16 class MassengeschmackTVIE(InfoExtractor):
  17     IE_NAME = 'massengeschmack.tv'
  18     _VALID_URL = r'https?://(?:www\.)?massengeschmack\.tv/play/(?P<id>[^?&#]+)'
  19
  20     _TEST = {
  21         'url': 'https://massengeschmack.tv/play/fktv202',
  22         'md5': 'a9e054db9c2b5a08f0a0527cc201e8d3',
  23         'info_dict': {
  24             'id': 'fktv202',
  25             'ext': 'mp4',
  26             'title': 'Fernsehkritik-TV - Folge 202',
  27         },
  28     }
  29
  30     def _real_extract(self, url):
  31         episode = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, episode)
  34         title = clean_html(self._html_search_regex(
  35             '<h3>([^<]+)</h3>', webpage, 'title'))
  36         thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
  37         sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
  38
  39         formats = []
  40         for source in sources:
  41             furl = source.get('src')
  42             if not furl:
  43                 continue
  44             furl = self._proto_relative_url(furl)
  45             ext = determine_ext(furl) or mimetype2ext(source.get('type'))
  46             if ext == 'm3u8':
  47                 formats.extend(self._extract_m3u8_formats(
  48                     furl, episode, 'mp4', 'm3u8_native',
  49                     m3u8_id='hls', fatal=False))
  50             else:
  51                 formats.append({
  52                     'url': furl,
  53                     'format_id': determine_ext(furl),
  54                 })
  55
  56         for (durl, format_id, width, height, filesize) in re.findall(r'''(?x)
  57                                    <a[^>]+?href="(?P<url>(?:https:)?//[^"]+)".*?
  58                                    <strong>(?P<format_id>.+?)</strong>.*?
  59                                    <small>(?:(?P<width>\d+)x(?P<height>\d+))?\s+?\((?P<filesize>[\d,]+\s*[GM]iB)\)</small>
  60                                 ''', webpage):
  61             formats.append({
  62                 'url': durl,
  63                 'format_id': format_id,
  64                 'width': int_or_none(width),
  65                 'height': int_or_none(height),
  66                 'filesize': parse_filesize(filesize),
  67                 'vcodec': 'none' if format_id.startswith('Audio') else None,
  68             })
  69
  70         self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr'))
  71
  72         return {
  73             'id': episode,
  74             'title': title,
  75             'formats': formats,
  76             'thumbnail': thumbnail,
  77         }