Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/camdemy.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import datetime
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse_urlencode,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     parse_iso8601,
  14     str_to_int,
  15 )
  16
  17
  18 class CamdemyIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
  20     _TESTS = [{
  21         # single file
  22         'url': 'http://www.camdemy.com/media/5181/',
  23         'md5': '5a5562b6a98b37873119102e052e311b',
  24         'info_dict': {
  25             'id': '5181',
  26             'ext': 'mp4',
  27             'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
  28             'thumbnail': 're:^https?://.*\.jpg$',
  29             'description': '',
  30             'creator': 'ss11spring',
  31             'upload_date': '20130114',
  32             'timestamp': 1358154556,
  33             'view_count': int,
  34         }
  35     }, {
  36         # With non-empty description
  37         'url': 'http://www.camdemy.com/media/13885',
  38         'md5': '4576a3bb2581f86c61044822adbd1249',
  39         'info_dict': {
  40             'id': '13885',
  41             'ext': 'mp4',
  42             'title': 'EverCam + Camdemy QuickStart',
  43             'thumbnail': 're:^https?://.*\.jpg$',
  44             'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
  45             'creator': 'evercam',
  46             'upload_date': '20140620',
  47             'timestamp': 1403271569,
  48         }
  49     }, {
  50         # External source
  51         'url': 'http://www.camdemy.com/media/14842',
  52         'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
  53         'info_dict': {
  54             'id': '2vsYQzNIsJo',
  55             'ext': 'mp4',
  56             'upload_date': '20130211',
  57             'uploader': 'Hun Kim',
  58             'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
  59             'uploader_id': 'hunkimtutorials',
  60             'title': 'Excel 2013 Tutorial - How to add Password Protection',
  61         }
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66         page = self._download_webpage(url, video_id)
  67
  68         src_from = self._html_search_regex(
  69             r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
  70             'external source', default=None)
  71         if src_from:
  72             return self.url_result(src_from)
  73
  74         oembed_obj = self._download_json(
  75             'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
  76
  77         thumb_url = oembed_obj['thumbnail_url']
  78         video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
  79         file_list_doc = self._download_xml(
  80             compat_urlparse.urljoin(video_folder, 'fileList.xml'),
  81             video_id, 'Filelist XML')
  82         file_name = file_list_doc.find('./video/item/fileName').text
  83         video_url = compat_urlparse.urljoin(video_folder, file_name)
  84
  85         timestamp = parse_iso8601(self._html_search_regex(
  86             r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
  87             page, 'creation time', fatal=False),
  88             delimiter=' ', timezone=datetime.timedelta(hours=8))
  89         view_count = str_to_int(self._html_search_regex(
  90             r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
  91             page, 'view count', fatal=False))
  92
  93         return {
  94             'id': video_id,
  95             'url': video_url,
  96             'title': oembed_obj['title'],
  97             'thumbnail': thumb_url,
  98             'description': self._html_search_meta('description', page),
  99             'creator': oembed_obj['author_name'],
 100             'duration': oembed_obj['duration'],
 101             'timestamp': timestamp,
 102             'view_count': view_count,
 103         }
 104
 105
 106 class CamdemyFolderIE(InfoExtractor):
 107     _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
 108     _TESTS = [{
 109         # links with trailing slash
 110         'url': 'http://www.camdemy.com/folder/450',
 111         'info_dict': {
 112             'id': '450',
 113             'title': '信號與系統 2012 & 2011 (Signals and Systems)',
 114         },
 115         'playlist_mincount': 145
 116     }, {
 117         # links without trailing slash
 118         # and multi-page
 119         'url': 'http://www.camdemy.com/folder/853',
 120         'info_dict': {
 121             'id': '853',
 122             'title': '科學計算 - 使用 Matlab'
 123         },
 124         'playlist_mincount': 20
 125     }, {
 126         # with displayMode parameter. For testing the codes to add parameters
 127         'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
 128         'info_dict': {
 129             'id': '853',
 130             'title': '科學計算 - 使用 Matlab'
 131         },
 132         'playlist_mincount': 20
 133     }]
 134
 135     def _real_extract(self, url):
 136         folder_id = self._match_id(url)
 137
 138         # Add displayMode=list so that all links are displayed in a single page
 139         parsed_url = list(compat_urlparse.urlparse(url))
 140         query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
 141         query.update({'displayMode': 'list'})
 142         parsed_url[4] = compat_urllib_parse_urlencode(query)
 143         final_url = compat_urlparse.urlunparse(parsed_url)
 144
 145         page = self._download_webpage(final_url, folder_id)
 146         matches = re.findall(r"href='(/media/\d+/?)'", page)
 147
 148         entries = [self.url_result('http://www.camdemy.com' + media_path)
 149                    for media_path in matches]
 150
 151         folder_title = self._html_search_meta('keywords', page)
 152
 153         return self.playlist_result(entries, folder_id, folder_title)