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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class PinkbikeIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?pinkbike\.com/video/(?P<id>[0-9]+)'
  11     _TESTS = [{
  12         'url': 'http://www.pinkbike.com/video/402811/',
  13         'md5': '4814b8ca7651034cd87e3361d5c2155a',
  14         'info_dict': {
  15             'id': '402811',
  16             'ext': 'mp4',
  17             'title': 'Brandon Semenuk - RAW 100',
  18             'thumbnail': 're:^https?://.*\.jpg$',
  19             'location': 'Victoria, British Columbia, Canada',
  20             'uploader_id': 'revelco',
  21             'upload_date': '20150406',
  22             'description': 'Official release: www.redbull.ca/rupertwalker',
  23             'duration': '100'
  24         }
  25     }, {
  26         'url': 'http://www.pinkbike.com/video/406629/',
  27         'md5': 'c7a3e19a2bd5cde5a1cda6b2b46caa74',
  28         'info_dict': {
  29             'id': '406629',
  30             'ext': 'mp4',
  31             'title': 'Chromag: Reece Wallace in Utah',
  32             'thumbnail': 're:^https?://.*\.jpg$',
  33             'location': 'Whistler, British Columbia, Canada',
  34             'uploader_id': 'Chromagbikes',
  35             'upload_date': '20150505',
  36             'description': 'Reece Wallace shredding Virgin, Utah. Video by Virtu Media.',
  37             'duration': '180'
  38         }
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44
  45         title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
  46         title = title[:-len(' Video - Pinkbike')]
  47
  48         description = self._html_search_meta('description', webpage, 'description')
  49         description = description[len(title + '. '):]
  50
  51         uploader_id = self._html_search_regex(r'un:\s*"(.*?)"', webpage, 'uploader_id')
  52
  53         upload_date = self._html_search_regex(
  54             r'class="fullTime"\s*title="([0-9]{4}(?:-[0-9]{2}){2})"',
  55             webpage, 'upload_date')
  56         upload_date = upload_date.replace('-', '')
  57
  58         location = self._html_search_regex(
  59             r'<dt>Location</dt>\n?\s*<dd>\n?(.*?)\s*<img',
  60             webpage, 'location')
  61
  62         formats = re.findall(
  63             r'<source data-quality=\\"([0-9]+)p\\" src=\\"(.*?)\\">',
  64             webpage)
  65
  66         formats = [{'url': fmt[1], 'height': fmt[0]} for fmt in formats]
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'description': description,
  72             'duration': self._html_search_meta('video:duration', webpage, 'duration'),
  73             'thumbnail': self._html_search_meta('og:image', webpage, 'thumbnail'),
  74             'uploader_id': uploader_id,
  75             'upload_date': upload_date,
  76             'location': location,
  77             'formats': formats
  78         }