yt_dlp/extractor/faz.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_etree_fromstring
   5 from ..utils import (
   6     int_or_none,
   7     xpath_element,
   8     xpath_text,
   9 )
  10
  11
  12 class FazIE(InfoExtractor):
  13     IE_NAME = 'faz.net'
  14     _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
  15
  16     _TESTS = [{
  17         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
  18         'info_dict': {
  19             'id': '12610585',
  20             'ext': 'mp4',
  21             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
  22             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
  23         },
  24     }, {
  25         'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  26         'only_matching': True,
  27     }, {
  28         'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  29         'only_matching': True,
  30     }, {
  31         'url': 'http://www.faz.net/-13659345.html',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.faz.net/foobarblafasel-13659345.html',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, video_id)
  45         description = self._og_search_description(webpage)
  46         media = self._html_search_regex(
  47             r"data-videojs-media='([^']+)",
  48             webpage, 'media')
  49         if media == 'extern':
  50             perform_url = self._search_regex(
  51                 r"<iframe[^>]+?src='((?:http:)?//player\.performgroup\.com/eplayer/eplayer\.html#/?[0-9a-f]{26}\.[0-9a-z]{26})",
  52                 webpage, 'perform url')
  53             return self.url_result(perform_url)
  54         config = compat_etree_fromstring(media)
  55
  56         encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
  57         formats = []
  58         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
  59             encoding = xpath_element(encodings, code)
  60             if encoding is not None:
  61                 encoding_url = xpath_text(encoding, 'FILENAME')
  62                 if encoding_url:
  63                     tbr = xpath_text(encoding, 'AVERAGEBITRATE', 1000)
  64                     if tbr:
  65                         tbr = int_or_none(tbr.replace(',', '.'))
  66                     f = {
  67                         'url': encoding_url,
  68                         'format_id': code.lower(),
  69                         'quality': pref,
  70                         'tbr': tbr,
  71                         'vcodec': xpath_text(encoding, 'CODEC'),
  72                     }
  73                     mobj = re.search(r'(\d+)x(\d+)_(\d+)\.mp4', encoding_url)
  74                     if mobj:
  75                         f.update({
  76                             'width': int(mobj.group(1)),
  77                             'height': int(mobj.group(2)),
  78                             'tbr': tbr or int(mobj.group(3)),
  79                         })
  80                     formats.append(f)
  81
  82         return {
  83             'id': video_id,
  84             'title': self._og_search_title(webpage),
  85             'formats': formats,
  86             'description': description.strip() if description else None,
  87             'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
  88             'duration': int_or_none(xpath_text(config, 'DURATION')),
  89         }