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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import parse_iso8601
   9
  10
  11 class CamdemyIE(InfoExtractor):
  12     _VALID_URL = r'http://www.camdemy.com/media/(?P<id>\d+).*'
  13     _TESTS = [{
  14         # single file
  15         'url': 'http://www.camdemy.com/media/5181/',
  16         'md5': '5a5562b6a98b37873119102e052e311b',
  17         'info_dict': {
  18             'id': '5181',
  19             'ext': 'mp4',
  20             'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22             'description': '',
  23             'creator': 'ss11spring',
  24             'upload_date': '20130114',
  25             'timestamp': 1358154556,
  26         }
  27     }, {
  28         # With non-empty description
  29         'url': 'http://www.camdemy.com/media/13885',
  30         'md5': '4576a3bb2581f86c61044822adbd1249',
  31         'info_dict': {
  32             'id': '13885',
  33             'ext': 'mp4',
  34             'title': 'EverCam + Camdemy QuickStart',
  35             'thumbnail': 're:^https?://.*\.jpg$',
  36             'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
  37             'creator': 'evercam',
  38             'upload_date': '20140620',
  39             'timestamp': 1403271569,
  40         }
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45
  46         page = self._download_webpage(url, video_id)
  47
  48         oembed_obj = self._download_json(
  49             'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
  50
  51         thumb_url = oembed_obj['thumbnail_url']
  52         video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
  53         fileListXML = self._download_xml(
  54             compat_urlparse.urljoin(video_folder, 'fileList.xml'),
  55             video_id, 'Filelist XML')
  56         fileName = fileListXML.find('./video/item/fileName').text
  57
  58         creation_time = self._html_search_regex(
  59             r"<div class='title'>Posted :</div>.*<div class='value'>([0-9:\- ]+)<",
  60             page, 'creation time', flags=re.MULTILINE | re.DOTALL) + '+08:00'
  61         creation_timestamp = parse_iso8601(creation_time, delimiter=' ')
  62
  63         view_count_str = self._html_search_regex(
  64             r"<div class='title'>Views :</div>.*<div class='value'>([0-9,]+)<",
  65             page, 'view count', flags=re.MULTILINE | re.DOTALL)
  66         views = int(view_count_str.replace(',', ''))
  67
  68         return {
  69             'id': video_id,
  70             'url': compat_urlparse.urljoin(video_folder, fileName),
  71             'title': oembed_obj['title'],
  72             'thumbnail': thumb_url,
  73             'description': self._html_search_meta('description', page),
  74             'creator': oembed_obj['author_name'],
  75             'duration': oembed_obj['duration'],
  76             'timestamp': creation_timestamp,
  77             'view_count': views,
  78         }