Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rts.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     int_or_none,
   9     parse_duration,
  10     parse_iso8601,
  11     unescapeHTML,
  12     compat_str,
  13 )
  14
  15
  16 class RTSIE(InfoExtractor):
  17     IE_DESC = 'RTS.ch'
  18     _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
  23             'md5': '753b877968ad8afaeddccc374d4256a5',
  24             'info_dict': {
  25                 'id': '3449373',
  26                 'ext': 'mp4',
  27                 'duration': 1488,
  28                 'title': 'Les Enfants Terribles',
  29                 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
  30                 'uploader': 'Divers',
  31                 'upload_date': '19680921',
  32                 'timestamp': -40280400,
  33                 'thumbnail': 're:^https?://.*\.image'
  34             },
  35         },
  36         {
  37             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
  38             'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',
  39             'info_dict': {
  40                 'id': '5624067',
  41                 'ext': 'mp4',
  42                 'duration': 3720,
  43                 'title': 'Les yeux dans les cieux - Mon homard au Canada',
  44                 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
  45                 'uploader': 'Passe-moi les jumelles',
  46                 'upload_date': '20140404',
  47                 'timestamp': 1396635300,
  48                 'thumbnail': 're:^https?://.*\.image'
  49             },
  50         },
  51         {
  52             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
  53             'md5': 'b4326fecd3eb64a458ba73c73e91299d',
  54             'info_dict': {
  55                 'id': '5745975',
  56                 'ext': 'mp4',
  57                 'duration': 48,
  58                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
  59                 'description': 'Hockey - Playoff',
  60                 'uploader': 'Hockey',
  61                 'upload_date': '20140403',
  62                 'timestamp': 1396556882,
  63                 'thumbnail': 're:^https?://.*\.image'
  64             },
  65             'skip': 'Blocked outside Switzerland',
  66         },
  67         {
  68             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
  69             'md5': '9bb06503773c07ce83d3cbd793cebb91',
  70             'info_dict': {
  71                 'id': '5745356',
  72                 'ext': 'mp4',
  73                 'duration': 33,
  74                 'title': 'Londres cachée par un épais smog',
  75                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
  76                 'uploader': 'Le Journal en continu',
  77                 'upload_date': '20140403',
  78                 'timestamp': 1396537322,
  79                 'thumbnail': 're:^https?://.*\.image'
  80             },
  81         },
  82         {
  83             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
  84             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
  85             'info_dict': {
  86                 'id': '5706148',
  87                 'ext': 'mp3',
  88                 'duration': 123,
  89                 'title': '"Urban Hippie", de Damien Krisl',
  90                 'description': 'Des Hippies super glam.',
  91                 'upload_date': '20140403',
  92                 'timestamp': 1396551600,
  93             },
  94         },
  95     ]
  96
  97     def _real_extract(self, url):
  98         m = re.match(self._VALID_URL, url)
  99         video_id = m.group('id')
 100
 101         def download_json(internal_id):
 102             return self._download_json(
 103                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
 104                 video_id)
 105
 106         all_info = download_json(video_id)
 107
 108         # video_id extracted out of URL is not always a real id
 109         if 'video' not in all_info and 'audio' not in all_info:
 110             page = self._download_webpage(url, video_id)
 111             internal_id = self._html_search_regex(
 112                 r'<(?:video|audio) data-id="([0-9]+)"', page,
 113                 'internal video id')
 114             all_info = download_json(internal_id)
 115
 116         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 117
 118         upload_timestamp = parse_iso8601(info.get('broadcast_date'))
 119         duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
 120         if isinstance(duration, compat_str):
 121             duration = parse_duration(duration)
 122         view_count = info.get('plays')
 123         thumbnail = unescapeHTML(info.get('preview_image_url'))
 124
 125         def extract_bitrate(url):
 126             return int_or_none(self._search_regex(
 127                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 128
 129         formats = [{
 130             'format_id': fid,
 131             'url': furl,
 132             'tbr': extract_bitrate(furl),
 133         } for fid, furl in info['streams'].items()]
 134
 135         if 'media' in info:
 136             formats.extend([{
 137                 'format_id': '%s-%sk' % (media['ext'], media['rate']),
 138                 'url': 'http://download-video.rts.ch/%s' % media['url'],
 139                 'tbr': media['rate'] or extract_bitrate(media['url']),
 140             } for media in info['media'] if media.get('rate')])
 141
 142         self._sort_formats(formats)
 143
 144         return {
 145             'id': video_id,
 146             'formats': formats,
 147             'title': info['title'],
 148             'description': info.get('intro'),
 149             'duration': duration,
 150             'view_count': view_count,
 151             'uploader': info.get('programName'),
 152             'timestamp': upload_timestamp,
 153             'thumbnail': thumbnail,
 154         }