youtube_dl/extractor/nfl.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     clean_html,
   9     determine_ext,
  10     get_element_by_class,
  11 )
  12
  13
  14 class NFLBaseIE(InfoExtractor):
  15     _VALID_URL_BASE = r'''(?x)
  16                     https?://
  17                         (?P<host>
  18                             (?:www\.)?
  19                             (?:
  20                                 (?:
  21                                     nfl|
  22                                     buffalobills|
  23                                     miamidolphins|
  24                                     patriots|
  25                                     newyorkjets|
  26                                     baltimoreravens|
  27                                     bengals|
  28                                     clevelandbrowns|
  29                                     steelers|
  30                                     houstontexans|
  31                                     colts|
  32                                     jaguars|
  33                                     (?:titansonline|tennesseetitans)|
  34                                     denverbroncos|
  35                                     (?:kc)?chiefs|
  36                                     raiders|
  37                                     chargers|
  38                                     dallascowboys|
  39                                     giants|
  40                                     philadelphiaeagles|
  41                                     (?:redskins|washingtonfootball)|
  42                                     chicagobears|
  43                                     detroitlions|
  44                                     packers|
  45                                     vikings|
  46                                     atlantafalcons|
  47                                     panthers|
  48                                     neworleanssaints|
  49                                     buccaneers|
  50                                     azcardinals|
  51                                     (?:stlouis|the)rams|
  52                                     49ers|
  53                                     seahawks
  54                                 )\.com|
  55                                 .+?\.clubs\.nfl\.com
  56                             )
  57                         )/
  58                     '''
  59     _VIDEO_CONFIG_REGEX = r'<script[^>]+id="[^"]*video-config-[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}[^"]*"[^>]*>\s*({.+})'
  60     _WORKING = False
  61
  62     def _parse_video_config(self, video_config, display_id):
  63         video_config = self._parse_json(video_config, display_id)
  64         item = video_config['playlist'][0]
  65         mcp_id = item.get('mcpID')
  66         if mcp_id:
  67             info = self.url_result(
  68                 'anvato:GXvEgwyJeWem8KCYXfeoHWknwP48Mboj:' + mcp_id,
  69                 'Anvato', mcp_id)
  70         else:
  71             media_id = item.get('id') or item['entityId']
  72             title = item['title']
  73             item_url = item['url']
  74             info = {'id': media_id}
  75             ext = determine_ext(item_url)
  76             if ext == 'm3u8':
  77                 info['formats'] = self._extract_m3u8_formats(item_url, media_id, 'mp4')
  78                 self._sort_formats(info['formats'])
  79             else:
  80                 info['url'] = item_url
  81                 if item.get('audio') is True:
  82                     info['vcodec'] = 'none'
  83             is_live = video_config.get('live') is True
  84             thumbnails = None
  85             image_url = item.get(item.get('imageSrc')) or item.get(item.get('posterImage'))
  86             if image_url:
  87                 thumbnails = [{
  88                     'url': image_url,
  89                     'ext': determine_ext(image_url, 'jpg'),
  90                 }]
  91             info.update({
  92                 'title': self._live_title(title) if is_live else title,
  93                 'is_live': is_live,
  94                 'description': clean_html(item.get('description')),
  95                 'thumbnails': thumbnails,
  96             })
  97         return info
  98
  99
 100 class NFLIE(NFLBaseIE):
 101     IE_NAME = 'nfl.com'
 102     _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'(?:videos?|listen|audio)/(?P<id>[^/#?&]+)'
 103     _TESTS = [{
 104         'url': 'https://www.nfl.com/videos/baker-mayfield-s-game-changing-plays-from-3-td-game-week-14',
 105         'info_dict': {
 106             'id': '899441',
 107             'ext': 'mp4',
 108             'title': "Baker Mayfield's game-changing plays from 3-TD game Week 14",
 109             'description': 'md5:85e05a3cc163f8c344340f220521136d',
 110             'upload_date': '20201215',
 111             'timestamp': 1608009755,
 112             'thumbnail': r're:^https?://.*\.jpg$',
 113             'uploader': 'NFL',
 114         }
 115     }, {
 116         'url': 'https://www.chiefs.com/listen/patrick-mahomes-travis-kelce-react-to-win-over-dolphins-the-breakdown',
 117         'md5': '6886b32c24b463038c760ceb55a34566',
 118         'info_dict': {
 119             'id': 'd87e8790-3e14-11eb-8ceb-ff05c2867f99',
 120             'ext': 'mp3',
 121             'title': 'Patrick Mahomes, Travis Kelce React to Win Over Dolphins | The Breakdown',
 122             'description': 'md5:12ada8ee70e6762658c30e223e095075',
 123         }
 124     }, {
 125         'url': 'https://www.buffalobills.com/video/buffalo-bills-military-recognition-week-14',
 126         'only_matching': True,
 127     }, {
 128         'url': 'https://www.raiders.com/audio/instant-reactions-raiders-week-14-loss-to-indianapolis-colts-espn-jason-fitz',
 129         'only_matching': True,
 130     }]
 131
 132     def _real_extract(self, url):
 133         display_id = self._match_id(url)
 134         webpage = self._download_webpage(url, display_id)
 135         return self._parse_video_config(self._search_regex(
 136             self._VIDEO_CONFIG_REGEX, webpage, 'video config'), display_id)
 137
 138
 139 class NFLArticleIE(NFLBaseIE):
 140     IE_NAME = 'nfl.com:article'
 141     _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'news/(?P<id>[^/#?&]+)'
 142     _TEST = {
 143         'url': 'https://www.buffalobills.com/news/the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
 144         'info_dict': {
 145             'id': 'the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
 146             'title': "'The only thing we've earned is the noise' | Bills coaches discuss handling rising expectations",
 147         },
 148         'playlist_count': 4,
 149     }
 150
 151     def _real_extract(self, url):
 152         display_id = self._match_id(url)
 153         webpage = self._download_webpage(url, display_id)
 154         entries = []
 155         for video_config in re.findall(self._VIDEO_CONFIG_REGEX, webpage):
 156             entries.append(self._parse_video_config(video_config, display_id))
 157         title = clean_html(get_element_by_class(
 158             'nfl-c-article__title', webpage)) or self._html_search_meta(
 159             ['og:title', 'twitter:title'], webpage)
 160         return self.playlist_result(entries, display_id, title)