yt_dlp/extractor/nfl.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     determine_ext,
   7     get_element_by_class,
   8 )
   9
  10
  11 class NFLBaseIE(InfoExtractor):
  12     _VALID_URL_BASE = r'''(?x)
  13                     https?://
  14                         (?P<host>
  15                             (?:www\.)?
  16                             (?:
  17                                 (?:
  18                                     nfl|
  19                                     buffalobills|
  20                                     miamidolphins|
  21                                     patriots|
  22                                     newyorkjets|
  23                                     baltimoreravens|
  24                                     bengals|
  25                                     clevelandbrowns|
  26                                     steelers|
  27                                     houstontexans|
  28                                     colts|
  29                                     jaguars|
  30                                     (?:titansonline|tennesseetitans)|
  31                                     denverbroncos|
  32                                     (?:kc)?chiefs|
  33                                     raiders|
  34                                     chargers|
  35                                     dallascowboys|
  36                                     giants|
  37                                     philadelphiaeagles|
  38                                     (?:redskins|washingtonfootball)|
  39                                     chicagobears|
  40                                     detroitlions|
  41                                     packers|
  42                                     vikings|
  43                                     atlantafalcons|
  44                                     panthers|
  45                                     neworleanssaints|
  46                                     buccaneers|
  47                                     azcardinals|
  48                                     (?:stlouis|the)rams|
  49                                     49ers|
  50                                     seahawks
  51                                 )\.com|
  52                                 .+?\.clubs\.nfl\.com
  53                             )
  54                         )/
  55                     '''
  56     _VIDEO_CONFIG_REGEX = r'<script[^>]+id="[^"]*video-config-[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}[^"]*"[^>]*>\s*({.+});?\s*</script>'
  57
  58     def _parse_video_config(self, video_config, display_id):
  59         video_config = self._parse_json(video_config, display_id)
  60         item = video_config['playlist'][0]
  61         mcp_id = item.get('mcpID')
  62         if mcp_id:
  63             info = self.url_result(
  64                 'anvato:GXvEgwyJeWem8KCYXfeoHWknwP48Mboj:' + mcp_id,
  65                 'Anvato', mcp_id)
  66         else:
  67             media_id = item.get('id') or item['entityId']
  68             title = item.get('title')
  69             item_url = item['url']
  70             info = {'id': media_id}
  71             ext = determine_ext(item_url)
  72             if ext == 'm3u8':
  73                 info['formats'] = self._extract_m3u8_formats(item_url, media_id, 'mp4')
  74             else:
  75                 info['url'] = item_url
  76                 if item.get('audio') is True:
  77                     info['vcodec'] = 'none'
  78             is_live = video_config.get('live') is True
  79             thumbnails = None
  80             image_url = item.get(item.get('imageSrc')) or item.get(item.get('posterImage'))
  81             if image_url:
  82                 thumbnails = [{
  83                     'url': image_url,
  84                     'ext': determine_ext(image_url, 'jpg'),
  85                 }]
  86             info.update({
  87                 'title': title,
  88                 'is_live': is_live,
  89                 'description': clean_html(item.get('description')),
  90                 'thumbnails': thumbnails,
  91             })
  92         return info
  93
  94
  95 class NFLIE(NFLBaseIE):
  96     IE_NAME = 'nfl.com'
  97     _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'(?:videos?|listen|audio)/(?P<id>[^/#?&]+)'
  98     _TESTS = [{
  99         'url': 'https://www.nfl.com/videos/baker-mayfield-s-game-changing-plays-from-3-td-game-week-14',
 100         'info_dict': {
 101             'id': '899441',
 102             'ext': 'mp4',
 103             'title': "Baker Mayfield's game-changing plays from 3-TD game Week 14",
 104             'description': 'md5:85e05a3cc163f8c344340f220521136d',
 105             'upload_date': '20201215',
 106             'timestamp': 1608009755,
 107             'thumbnail': r're:^https?://.*\.jpg$',
 108             'uploader': 'NFL',
 109             'tags': 'count:6',
 110             'duration': 157,
 111             'categories': 'count:3',
 112         }
 113     }, {
 114         'url': 'https://www.chiefs.com/listen/patrick-mahomes-travis-kelce-react-to-win-over-dolphins-the-breakdown',
 115         'md5': '6886b32c24b463038c760ceb55a34566',
 116         'info_dict': {
 117             'id': 'd87e8790-3e14-11eb-8ceb-ff05c2867f99',
 118             'ext': 'mp3',
 119             'title': 'Patrick Mahomes, Travis Kelce React to Win Over Dolphins | The Breakdown',
 120             'description': 'md5:12ada8ee70e6762658c30e223e095075',
 121         },
 122         'skip': 'HTTP Error 404: Not Found',
 123     }, {
 124         'url': 'https://www.buffalobills.com/video/buffalo-bills-military-recognition-week-14',
 125         'only_matching': True,
 126     }, {
 127         'url': 'https://www.raiders.com/audio/instant-reactions-raiders-week-14-loss-to-indianapolis-colts-espn-jason-fitz',
 128         'only_matching': True,
 129     }]
 130
 131     def _real_extract(self, url):
 132         display_id = self._match_id(url)
 133         webpage = self._download_webpage(url, display_id)
 134         return self._parse_video_config(self._search_regex(
 135             self._VIDEO_CONFIG_REGEX, webpage, 'video config'), display_id)
 136
 137
 138 class NFLArticleIE(NFLBaseIE):
 139     IE_NAME = 'nfl.com:article'
 140     _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'news/(?P<id>[^/#?&]+)'
 141     _TEST = {
 142         'url': 'https://www.buffalobills.com/news/the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
 143         'info_dict': {
 144             'id': 'the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
 145             'title': "'The only thing we've earned is the noise' | Bills coaches discuss handling rising expectations",
 146         },
 147         'playlist_count': 4,
 148     }
 149
 150     def _real_extract(self, url):
 151         display_id = self._match_id(url)
 152         webpage = self._download_webpage(url, display_id)
 153         entries = []
 154         for video_config in re.findall(self._VIDEO_CONFIG_REGEX, webpage):
 155             entries.append(self._parse_video_config(video_config, display_id))
 156         title = clean_html(get_element_by_class(
 157             'nfl-c-article__title', webpage)) or self._html_search_meta(
 158             ['og:title', 'twitter:title'], webpage)
 159         return self.playlist_result(entries, display_id, title)