youtube_dl/extractor/cda.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     decode_packed_codes,
   9     ExtractorError,
  10     parse_duration
  11 )
  12
  13
  14 class CDAIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
  16     _TESTS = [{
  17         'url': 'http://www.cda.pl/video/5749950c',
  18         'md5': '6f844bf51b15f31fae165365707ae970',
  19         'info_dict': {
  20             'id': '5749950c',
  21             'ext': 'mp4',
  22             'height': 720,
  23             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
  24             'duration': 39
  25         }
  26     }, {
  27         'url': 'http://www.cda.pl/video/57413289',
  28         'md5': 'a88828770a8310fc00be6c95faf7f4d5',
  29         'info_dict': {
  30             'id': '57413289',
  31             'ext': 'mp4',
  32             'title': 'Lądowanie na lotnisku na Maderze',
  33             'duration': 137
  34         }
  35     }, {
  36         'url': 'http://ebd.cda.pl/0x0/5749950c',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
  43
  44         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
  45             raise ExtractorError('This video is only available for premium users.', expected=True)
  46
  47         title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
  48
  49         formats = []
  50
  51         info_dict = {
  52             'id': video_id,
  53             'title': title,
  54             'formats': formats,
  55             'duration': None,
  56         }
  57
  58         def extract_format(page, version):
  59             unpacked = decode_packed_codes(page)
  60             format_url = self._search_regex(
  61                 r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False)
  62             if not format_url:
  63                 return
  64             f = {
  65                 'url': format_url,
  66             }
  67             m = re.search(
  68                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
  69                 page)
  70             if m:
  71                 f.update({
  72                     'format_id': m.group('format_id'),
  73                     'height': int(m.group('height')),
  74                 })
  75             info_dict['formats'].append(f)
  76             if not info_dict['duration']:
  77                 info_dict['duration'] = parse_duration(self._search_regex(
  78                     r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False))
  79
  80         extract_format(webpage, 'default')
  81
  82         for href, resolution in re.findall(
  83                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
  84                 webpage):
  85             webpage = self._download_webpage(
  86                 href, video_id, 'Downloading %s version information' % resolution, fatal=False)
  87             if not webpage:
  88                 # Manually report warning because empty page is returned when
  89                 # invalid version is requested.
  90                 self.report_warning('Unable to download %s version information' % resolution)
  91                 continue
  92             extract_format(webpage, resolution)
  93
  94         self._sort_formats(formats)
  95
  96         return info_dict