Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/onet.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     determine_ext,
   9     ExtractorError,
  10     float_or_none,
  11     get_element_by_class,
  12     int_or_none,
  13     js_to_json,
  14     parse_iso8601,
  15     remove_start,
  16     strip_or_none,
  17     url_basename,
  18 )
  19
  20
  21 class OnetBaseIE(InfoExtractor):
  22     def _search_mvp_id(self, webpage):
  23         return self._search_regex(
  24             r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
  25
  26     def _extract_from_id(self, video_id, webpage=None):
  27         response = self._download_json(
  28             'http://qi.ckm.onetapi.pl/', video_id,
  29             query={
  30                 'body[id]': video_id,
  31                 'body[jsonrpc]': '2.0',
  32                 'body[method]': 'get_asset_detail',
  33                 'body[params][ID_Publikacji]': video_id,
  34                 'body[params][Service]': 'www.onet.pl',
  35                 'content-type': 'application/jsonp',
  36                 'x-onet-app': 'player.front.onetapi.pl',
  37             })
  38
  39         error = response.get('error')
  40         if error:
  41             raise ExtractorError(
  42                 '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
  43
  44         video = response['result'].get('0')
  45
  46         formats = []
  47         for _, formats_dict in video['formats'].items():
  48             if not isinstance(formats_dict, dict):
  49                 continue
  50             for format_id, format_list in formats_dict.items():
  51                 if not isinstance(format_list, list):
  52                     continue
  53                 for f in format_list:
  54                     video_url = f.get('url')
  55                     if not video_url:
  56                         continue
  57                     ext = determine_ext(video_url)
  58                     if format_id == 'ism':
  59                         formats.extend(self._extract_ism_formats(
  60                             video_url, video_id, 'mss', fatal=False))
  61                     elif ext == 'mpd':
  62                         formats.extend(self._extract_mpd_formats(
  63                             video_url, video_id, mpd_id='dash', fatal=False))
  64                     else:
  65                         formats.append({
  66                             'url': video_url,
  67                             'format_id': format_id,
  68                             'height': int_or_none(f.get('vertical_resolution')),
  69                             'width': int_or_none(f.get('horizontal_resolution')),
  70                             'abr': float_or_none(f.get('audio_bitrate')),
  71                             'vbr': float_or_none(f.get('video_bitrate')),
  72                         })
  73         self._sort_formats(formats)
  74
  75         meta = video.get('meta', {})
  76
  77         title = (self._og_search_title(
  78             webpage, default=None) if webpage else None) or meta['title']
  79         description = (self._og_search_description(
  80             webpage, default=None) if webpage else None) or meta.get('description')
  81         duration = meta.get('length') or meta.get('lenght')
  82         timestamp = parse_iso8601(meta.get('addDate'), ' ')
  83
  84         return {
  85             'id': video_id,
  86             'title': title,
  87             'description': description,
  88             'duration': duration,
  89             'timestamp': timestamp,
  90             'formats': formats,
  91         }
  92
  93
  94 class OnetMVPIE(OnetBaseIE):
  95     _VALID_URL = r'onetmvp:(?P<id>\d+\.\d+)'
  96
  97     _TEST = {
  98         'url': 'onetmvp:381027.1509591944',
  99         'only_matching': True,
 100     }
 101
 102     def _real_extract(self, url):
 103         return self._extract_from_id(self._match_id(url))
 104
 105
 106 class OnetIE(OnetBaseIE):
 107     _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
 108     IE_NAME = 'onet.tv'
 109
 110     _TEST = {
 111         'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
 112         'md5': 'e3ffbf47590032ac3f27249204173d50',
 113         'info_dict': {
 114             'id': 'qbpyqc',
 115             'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd',
 116             'ext': 'mp4',
 117             'title': 'Open\'er Festival 2016: najdziwniejsze wymagania gwiazd',
 118             'description': 'Trzy samochody, których nigdy nie użyto, prywatne spa, hotel dekorowany czarnym suknem czy nielegalne używki. Organizatorzy koncertów i festiwali muszą stawać przed nie lada wyzwaniem zapraszając gwia...',
 119             'upload_date': '20160705',
 120             'timestamp': 1467721580,
 121         },
 122     }
 123
 124     def _real_extract(self, url):
 125         mobj = re.match(self._VALID_URL, url)
 126         display_id, video_id = mobj.group('display_id', 'id')
 127
 128         webpage = self._download_webpage(url, display_id)
 129
 130         mvp_id = self._search_mvp_id(webpage)
 131
 132         info_dict = self._extract_from_id(mvp_id, webpage)
 133         info_dict.update({
 134             'id': video_id,
 135             'display_id': display_id,
 136         })
 137
 138         return info_dict
 139
 140
 141 class OnetChannelIE(OnetBaseIE):
 142     _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P<id>[a-z]+)(?:[?#]|$)'
 143     IE_NAME = 'onet.tv:channel'
 144
 145     _TEST = {
 146         'url': 'http://onet.tv/k/openerfestival',
 147         'info_dict': {
 148             'id': 'openerfestival',
 149             'title': 'Open\'er Festival Live',
 150             'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.',
 151         },
 152         'playlist_mincount': 46,
 153     }
 154
 155     def _real_extract(self, url):
 156         channel_id = self._match_id(url)
 157
 158         webpage = self._download_webpage(url, channel_id)
 159
 160         current_clip_info = self._parse_json(self._search_regex(
 161             r'var\s+currentClip\s*=\s*({[^}]+})', webpage, 'video info'), channel_id,
 162             transform_source=lambda s: js_to_json(re.sub(r'\'\s*\+\s*\'', '', s)))
 163         video_id = remove_start(current_clip_info['ckmId'], 'mvp:')
 164         video_name = url_basename(current_clip_info['url'])
 165
 166         if self._downloader.params.get('noplaylist'):
 167             self.to_screen(
 168                 'Downloading just video %s because of --no-playlist' % video_name)
 169             return self._extract_from_id(video_id, webpage)
 170
 171         self.to_screen(
 172             'Downloading channel %s - add --no-playlist to just download video %s' % (
 173                 channel_id, video_name))
 174         matches = re.findall(
 175             r'<a[^>]+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)',
 176             webpage)
 177         entries = [
 178             self.url_result(video_link, OnetIE.ie_key())
 179             for video_link in matches]
 180
 181         channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
 182         channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
 183         return self.playlist_result(entries, channel_id, channel_title, channel_description)
 184
 185
 186 class OnetPlIE(InfoExtractor):
 187     _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P<id>[0-9a-z]+)'
 188     IE_NAME = 'onet.pl'
 189
 190     _TESTS = [{
 191         'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly',
 192         'md5': 'b94021eb56214c3969380388b6e73cb0',
 193         'info_dict': {
 194             'id': '1561707.1685479',
 195             'ext': 'mp4',
 196             'title': 'Ziobro wygrał kwalifikacje w Pjongczangu',
 197             'description': 'md5:61fb0740084d2d702ea96512a03585b4',
 198             'upload_date': '20170214',
 199             'timestamp': 1487078046,
 200         },
 201     }, {
 202         'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3',
 203         'only_matching': True,
 204     }, {
 205         'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e',
 206         'only_matching': True,
 207     }, {
 208         'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk',
 209         'only_matching': True,
 210     }, {
 211         'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89',
 212         'only_matching': True,
 213     }]
 214
 215     def _real_extract(self, url):
 216         video_id = self._match_id(url)
 217
 218         webpage = self._download_webpage(url, video_id)
 219
 220         mvp_id = self._search_regex(
 221             r'data-params-mvp=["\'](\d+\.\d+)', webpage, 'mvp id')
 222
 223         return self.url_result(
 224             'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id)