yt_dlp/extractor/pinkbike.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     remove_end,
   7     remove_start,
   8     str_to_int,
   9     unified_strdate,
  10 )
  11
  12
  13 class PinkbikeIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:(?:www\.)?pinkbike\.com/video/|es\.pinkbike\.org/i/kvid/kvid-y5\.swf\?id=)(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         'url': 'http://www.pinkbike.com/video/402811/',
  17         'md5': '4814b8ca7651034cd87e3361d5c2155a',
  18         'info_dict': {
  19             'id': '402811',
  20             'ext': 'mp4',
  21             'title': 'Brandon Semenuk - RAW 100',
  22             'description': 'Official release: www.redbull.ca/rupertwalker',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'duration': 100,
  25             'upload_date': '20150406',
  26             'uploader': 'revelco',
  27             'location': 'Victoria, British Columbia, Canada',
  28             'view_count': int,
  29             'comment_count': int,
  30         },
  31     }, {
  32         'url': 'http://es.pinkbike.org/i/kvid/kvid-y5.swf?id=406629',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(
  40             f'http://www.pinkbike.com/video/{video_id}', video_id)
  41
  42         formats = []
  43         for _, format_id, src in re.findall(
  44                 r'data-quality=((?:\\)?["\'])(.+?)\1[^>]+src=\1(.+?)\1', webpage):
  45             height = int_or_none(self._search_regex(
  46                 r'^(\d+)[pP]$', format_id, 'height', default=None))
  47             formats.append({
  48                 'url': src,
  49                 'format_id': format_id,
  50                 'height': height,
  51             })
  52
  53         title = remove_end(self._og_search_title(webpage), ' Video - Pinkbike')
  54         description = self._html_search_regex(
  55             r'(?s)id="media-description"[^>]*>(.+?)<',
  56             webpage, 'description', default=None) or remove_start(
  57             self._og_search_description(webpage), title + '. ')
  58         thumbnail = self._og_search_thumbnail(webpage)
  59         duration = int_or_none(self._html_search_meta(
  60             'video:duration', webpage, 'duration'))
  61
  62         uploader = self._search_regex(
  63             r'<a[^>]+\brel=["\']author[^>]+>([^<]+)', webpage,
  64             'uploader', fatal=False)
  65         upload_date = unified_strdate(self._search_regex(
  66             r'class="fullTime"[^>]+title="([^"]+)"',
  67             webpage, 'upload date', fatal=False))
  68
  69         location = self._html_search_regex(
  70             r'(?s)<dt>Location</dt>\s*<dd>(.+?)<',
  71             webpage, 'location', fatal=False)
  72
  73         def extract_count(webpage, label):
  74             return str_to_int(self._search_regex(
  75                 rf'<span[^>]+class="stat-num"[^>]*>([\d,.]+)</span>\s*<span[^>]+class="stat-label"[^>]*>{label}',
  76                 webpage, label, fatal=False))
  77
  78         view_count = extract_count(webpage, 'Views')
  79         comment_count = extract_count(webpage, 'Comments')
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'description': description,
  85             'thumbnail': thumbnail,
  86             'duration': duration,
  87             'upload_date': upload_date,
  88             'uploader': uploader,
  89             'location': location,
  90             'view_count': view_count,
  91             'comment_count': comment_count,
  92             'formats': formats,
  93         }