_ Git - youtube-dl/blob - youtube_dl/extractor/seznamzpravy.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_parse_qs,
   7     compat_str,
   8     compat_urllib_parse_urlparse,
   9 )
  10 from ..utils import (
  11     urljoin,
  12     int_or_none,
  13     try_get,
  14     update_url_query,
  15 )
  16
  17
  18 def _raw_id(src_url):
  19     return compat_urllib_parse_urlparse(src_url).path.split('/')[-1]
  20
  21
  22 class SeznamZpravyIE(InfoExtractor):
  23     _VALID_URL = r'https?://(?:www\.)?(?:seznam\.cz/zpravy|seznamzpravy\.cz)/iframe/player\?.*\bsrc='
  24     _TESTS = [{
  25         'url': r'https://www.seznamzpravy.cz/iframe/player?duration=241&serviceSlug=zpravy&src=https%3A%2F%2Fv39-a.sdn.szn.cz%2Fv_39%2Fvmd%2F5999c902ea707c67d8e267a9%3Ffl%3Dmdk%2C432f65a0%7C&itemType=video&autoPlay=false&title=Sv%C4%9Bt%20bez%20obalu%3A%20%C4%8Ce%C5%A1t%C3%AD%20voj%C3%A1ci%20na%20mis%C3%ADch%20(kr%C3%A1tk%C3%A1%20verze)&series=Sv%C4%9Bt%20bez%20obalu&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_F_I%2FR5puJ.jpeg%3Ffl%3Dcro%2C0%2C0%2C1920%2C1080%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=1920&height=1080&cutFrom=0&cutTo=0&splVersion=VOD&contentId=170889&contextId=35990&showAdvert=true&collocation=&autoplayPossible=true&embed=&isVideoTooShortForPreroll=false&isVideoTooLongForPostroll=true&videoCommentOpKey=&videoCommentId=&version=4.0.76&dotService=zpravy&gemiusPrismIdentifier=bVc1ZIb_Qax4W2v5xOPGpMeCP31kFfrTzj0SqPTLh_b.Z7&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy',
  26         'params': {'skip_download': True},  # 'file_minsize': 1586 seems to get killed in test_download.py
  27         'info_dict': {
  28             'id': '170889',
  29             'ext': 'mp4',
  30             'title': 'Svět bez obalu: Čeští vojáci na misích (krátká verze)',
  31         }
  32     }]
  33
  34     def _extract_sdn_formats(self, sdn_url, video_id):
  35         sdn_data = self._download_json(sdn_url, video_id)
  36         formats = []
  37         mp4_formats = try_get(sdn_data, lambda x: x['data']['mp4'], dict) or {}
  38         for fmt, fmtdata in mp4_formats.items():
  39             relative_url = fmtdata.get('url')
  40             if not relative_url:
  41                 continue
  42
  43             try:
  44                 width, height = fmtdata.get('resolution')
  45             except (TypeError, ValueError):
  46                 width, height = None, None
  47
  48             formats.append({
  49                 'format_id': fmt,
  50                 'width': int_or_none(width),
  51                 'height': int_or_none(height),
  52                 'url': urljoin(sdn_url, relative_url),
  53                 'vcodec': fmtdata.get('codec'),
  54                 'tbr': int_or_none(fmtdata.get('bandwidth'), scale=1000),
  55                 'duration': int_or_none(fmtdata.get('duration'), scale=1000),
  56             })
  57
  58         playlists = sdn_data.get('pls', {})
  59         dash_rel_url = try_get(playlists, lambda x: x['dash']['url'], compat_str)
  60         if dash_rel_url:
  61             formats.extend(self._extract_mpd_formats(urljoin(sdn_url, dash_rel_url), video_id, mpd_id='dash', fatal=False))
  62
  63         hls_rel_url = try_get(playlists, lambda x: x['hls']['url'], compat_str)
  64         if hls_rel_url:
  65             formats.extend(self._extract_m3u8_formats(urljoin(sdn_url, hls_rel_url), video_id, ext='mp4', m3u8_id='hls', fatal=False))
  66
  67         self._sort_formats(formats)
  68         return formats
  69
  70     def _real_extract(self, url):
  71         params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
  72         src = params['src'][0]
  73         video_id = params.get('contentId', [_raw_id(src)])[0]
  74
  75         return {
  76             'id': video_id,
  77             'title': params['title'][0],
  78             'formats': self._extract_sdn_formats(src + 'spl2,2,VOD', video_id),
  79         }
  80
  81
  82 class SeznamZpravyArticleIE(InfoExtractor):
  83     _VALID_URL = r'https?://(?:www\.)?(?:seznam\.cz/zpravy|seznamzpravy\.cz)/clanek/(?:[-a-z0-9]+)-(?P<id>[0-9]+)'
  84     _API_URL = 'https://apizpravy.seznam.cz/'
  85
  86     _TESTS = [{
  87         # two videos on one page, with SDN URL
  88         'url': 'https://www.seznamzpravy.cz/clanek/jejich-svet-na-nas-utoci-je-lepsi-branit-se-na-jejich-pisecku-rika-reziser-a-major-v-zaloze-marhoul-35990',
  89         'params': {'skip_download': True},
  90         # ^ this is here instead of 'file_minsize': 1586, which does not work because
  91         #   test_download.py forces expected_minsize to at least 10k when test is running
  92         'info_dict': {
  93             'id': '170889',
  94             'ext': 'mp4',
  95             'title': 'Svět bez obalu: Čeští vojáci na misích (krátká verze)',
  96         }
  97     }, {
  98         # video with live stream URL
  99         'url': 'https://www.seznam.cz/zpravy/clanek/znovu-do-vlady-s-ano-pavel-belobradek-ve-volebnim-specialu-seznamu-38489',
 100         'info_dict': {
 101             'id': '185688',
 102             'ext': 'mp4',
 103             'title': 'Předseda KDU-ČSL Pavel Bělobrádek ve volební Výzvě Seznamu',
 104         }
 105     }]
 106
 107     def _extract_caption(self, api_data, article_id):
 108         title = api_data.get('title') or api_data.get('captionTitle')
 109         caption = api_data.get('caption')
 110         if not title or not caption:
 111             return {}
 112
 113         if 'sdn' in caption.get('video', {}):
 114             src_url = caption['video']['sdn']
 115         elif 'liveStreamUrl' in caption:
 116             src_url = self._download_json(caption['liveStreamUrl'], article_id)['Location']
 117         else:
 118             return {}
 119
 120         return {
 121             'id': caption.get('uid'),
 122             'title': caption.get('title'),
 123             'src': src_url,
 124         }
 125
 126     def _extract_content(self, api_data):
 127         entries = []
 128         for item in api_data.get('content', []):
 129             media = item.get('properties', {}).get('media', {})
 130             src_url = media.get('video', {}).get('sdn')
 131             title = media.get('title')
 132             if not src_url or not title:
 133                 continue
 134
 135             entries.append({
 136                 'id': media.get('uid'),
 137                 'title': title,
 138                 'src': src_url,
 139             })
 140
 141         return entries
 142
 143     def _iframe_result(self, info_dict):
 144         video_id = info_dict['id'] or _raw_id(info_dict['src'])
 145         url = update_url_query('https://www.seznam.cz/zpravy/iframe/player', {
 146             'src': info_dict['src'],
 147             'title': info_dict['title'],
 148             'contentId': video_id,
 149             'serviceName': 'Seznam Zprávy',
 150         })
 151         return self.url_result(url, ie='SeznamZpravy', video_id=video_id, video_title=info_dict['title'])
 152
 153     def _real_extract(self, url):
 154         article_id = self._match_id(url)
 155         api_data = self._download_json(self._API_URL + 'v1/documents/' + article_id, article_id)
 156
 157         caption = self._extract_caption(api_data, article_id)
 158         content = self._extract_content(api_data)
 159
 160         if caption and not content:
 161             return self._iframe_result(caption)
 162         else:
 163             if caption:
 164                 content.insert(0, caption)
 165             return self.playlist_result(
 166                 [self._iframe_result(x) for x in content],
 167                 playlist_id=article_id,
 168                 playlist_title=api_data.get('title') or caption.get('title')
 169             )