]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/screencast.py
[dailymotion] Error spelling
[youtube-dl] / youtube_dl / extractor / screencast.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import (
6     compat_parse_qs,
7     compat_urllib_request,
8 )
9 from ..utils import (
10     ExtractorError,
11 )
12
13
14 class ScreencastIE(InfoExtractor):
15     _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
16     _TESTS = [{
17         'url': 'http://www.screencast.com/t/3ZEjQXlT',
18         'md5': '917df1c13798a3e96211dd1561fded83',
19         'info_dict': {
20             'id': '3ZEjQXlT',
21             'ext': 'm4v',
22             'title': 'Color Measurement with Ocean Optics Spectrometers',
23             'description': 'md5:240369cde69d8bed61349a199c5fb153',
24             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
25         }
26     }, {
27         'url': 'http://www.screencast.com/t/V2uXehPJa1ZI',
28         'md5': 'e8e4b375a7660a9e7e35c33973410d34',
29         'info_dict': {
30             'id': 'V2uXehPJa1ZI',
31             'ext': 'mov',
32             'title': 'The Amadeus Spectrometer',
33             'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit',
34             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
35         }
36     }, {
37         'url': 'http://www.screencast.com/t/aAB3iowa',
38         'md5': 'dedb2734ed00c9755761ccaee88527cd',
39         'info_dict': {
40             'id': 'aAB3iowa',
41             'ext': 'mp4',
42             'title': 'Google Earth Export',
43             'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.',
44             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
45         }
46     }, {
47         'url': 'http://www.screencast.com/t/X3ddTrYh',
48         'md5': '669ee55ff9c51988b4ebc0877cc8b159',
49         'info_dict': {
50             'id': 'X3ddTrYh',
51             'ext': 'wmv',
52             'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression',
53             'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
54             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
55         }
56     },
57     ]
58
59     def _real_extract(self, url):
60         video_id = self._match_id(url)
61         webpage = self._download_webpage(url, video_id)
62
63         video_url = self._html_search_regex(
64             r'<embed name="Video".*?src="([^"]+)"', webpage,
65             'QuickTime embed', default=None)
66
67         if video_url is None:
68             flash_vars_s = self._html_search_regex(
69                 r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
70                 default=None)
71             if not flash_vars_s:
72                 flash_vars_s = self._html_search_regex(
73                     r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars',
74                     default=None)
75                 if flash_vars_s:
76                     flash_vars_s = flash_vars_s.replace(',', '&')
77             if flash_vars_s:
78                 flash_vars = compat_parse_qs(flash_vars_s)
79                 video_url_raw = compat_urllib_request.quote(
80                     flash_vars['content'][0])
81                 video_url = video_url_raw.replace('http%3A', 'http:')
82
83         if video_url is None:
84             video_meta = self._html_search_meta(
85                 'og:video', webpage, default=None)
86             if video_meta:
87                 video_url = self._search_regex(
88                     r'src=(.*?)(?:$|&)', video_meta,
89                     'meta tag video URL', default=None)
90
91         if video_url is None:
92             raise ExtractorError('Cannot find video')
93
94         title = self._og_search_title(webpage, default=None)
95         if title is None:
96             title = self._html_search_regex(
97                 [r'<b>Title:</b> ([^<]*)</div>',
98                  r'class="tabSeperator">></span><span class="tabText">(.*?)<'],
99                 webpage, 'title')
100         thumbnail = self._og_search_thumbnail(webpage)
101         description = self._og_search_description(webpage, default=None)
102         if description is None:
103             description = self._html_search_meta('description', webpage)
104
105         return {
106             'id': video_id,
107             'url': video_url,
108             'title': title,
109             'description': description,
110             'thumbnail': thumbnail,
111         }