youtube_dl/extractor/faz.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_etree_fromstring
   8 from ..utils import (
   9     xpath_element,
  10     xpath_text,
  11     int_or_none,
  12 )
  13
  14
  15 class FazIE(InfoExtractor):
  16     IE_NAME = 'faz.net'
  17     _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
  18
  19     _TESTS = [{
  20         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
  21         'info_dict': {
  22             'id': '12610585',
  23             'ext': 'mp4',
  24             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
  25             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
  26         },
  27     }, {
  28         'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  29         'only_matching': True,
  30     }, {
  31         'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.faz.net/-13659345.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.faz.net/foobarblafasel-13659345.html',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         webpage = self._download_webpage(url, video_id)
  48         description = self._og_search_description(webpage)
  49         media = self._html_search_regex(
  50             r"data-videojs-media='([^']+)",
  51             webpage, 'media')
  52         if media == 'extern':
  53             perform_url = self._search_regex(
  54                 r"<iframe[^>]+?src='((?:http:)?//player\.performgroup\.com/eplayer/eplayer\.html#/?[0-9a-f]{26}\.[0-9a-z]{26})",
  55                 webpage, 'perform url')
  56             return self.url_result(perform_url)
  57         config = compat_etree_fromstring(media)
  58
  59         encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
  60         formats = []
  61         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
  62             encoding = xpath_element(encodings, code)
  63             if encoding is not None:
  64                 encoding_url = xpath_text(encoding, 'FILENAME')
  65                 if encoding_url:
  66                     tbr = xpath_text(encoding, 'AVERAGEBITRATE', 1000)
  67                     if tbr:
  68                         tbr = int_or_none(tbr.replace(',', '.'))
  69                     f = {
  70                         'url': encoding_url,
  71                         'format_id': code.lower(),
  72                         'quality': pref,
  73                         'tbr': tbr,
  74                         'vcodec': xpath_text(encoding, 'CODEC'),
  75                     }
  76                     mobj = re.search(r'(\d+)x(\d+)_(\d+)\.mp4', encoding_url)
  77                     if mobj:
  78                         f.update({
  79                             'width': int(mobj.group(1)),
  80                             'height': int(mobj.group(2)),
  81                             'tbr': tbr or int(mobj.group(3)),
  82                         })
  83                     formats.append(f)
  84         self._sort_formats(formats)
  85
  86         return {
  87             'id': video_id,
  88             'title': self._og_search_title(webpage),
  89             'formats': formats,
  90             'description': description.strip() if description else None,
  91             'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
  92             'duration': int_or_none(xpath_text(config, 'DURATION')),
  93         }