aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/camdemy.py
blob: 0d64b5a16d2893749e80fbd82489e3521cdfbcd2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import parse_iso8601


class CamdemyIE(InfoExtractor):
    _VALID_URL = r'http://www.camdemy.com/media/(?P<id>\d+)'
    _TESTS = [{
        # single file
        'url': 'http://www.camdemy.com/media/5181/',
        'md5': '5a5562b6a98b37873119102e052e311b',
        'info_dict': {
            'id': '5181',
            'ext': 'mp4',
            'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
            'thumbnail': 're:^https?://.*\.jpg$',
            'description': '',
            'creator': 'ss11spring',
            'upload_date': '20130114',
            'timestamp': 1358154556,
        }
    }, {
        # With non-empty description
        'url': 'http://www.camdemy.com/media/13885',
        'md5': '4576a3bb2581f86c61044822adbd1249',
        'info_dict': {
            'id': '13885',
            'ext': 'mp4',
            'title': 'EverCam + Camdemy QuickStart',
            'thumbnail': 're:^https?://.*\.jpg$',
            'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
            'creator': 'evercam',
            'upload_date': '20140620',
            'timestamp': 1403271569,
        }
    }, {
        # External source
        'url': 'http://www.camdemy.com/media/14842',
        'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
        'info_dict': {
            'id': '2vsYQzNIsJo',
            'ext': 'mp4',
            'upload_date': '20130211',
            'uploader': 'Hun Kim',
            'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
            'uploader_id': 'hunkimtutorials',
            'title': 'Excel 2013 Tutorial - How to add Password Protection',
        }
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        page = self._download_webpage(url, video_id)

        srcFrom = self._html_search_regex(
            r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
            'external source', default=None)

        if srcFrom:
            return self.url_result(srcFrom)

        oembed_obj = self._download_json(
            'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)

        thumb_url = oembed_obj['thumbnail_url']
        video_folder = compat_urllib_parse.urljoin(thumb_url, 'video/')
        fileListXML = self._download_xml(
            compat_urllib_parse.urljoin(video_folder, 'fileList.xml'),
            video_id, 'Filelist XML')
        fileName = fileListXML.find('./video/item/fileName').text

        creation_time = self._html_search_regex(
            r"<div class='title'>Posted :</div>[\r\n ]*<div class='value'>([^<>]+)<",
            page, 'creation time', flags=re.MULTILINE) + '+08:00'
        creation_timestamp = parse_iso8601(creation_time, delimiter=' ')

        view_count_str = self._html_search_regex(
            r"<div class='title'>Views :</div>[\r\n ]*<div class='value'>([^<>]+)<",
            page, 'view count', flags=re.MULTILINE)
        views = int(view_count_str.replace(',', ''))

        return {
            'id': video_id,
            'url': compat_urllib_parse.urljoin(video_folder, fileName),
            'title': oembed_obj['title'],
            'thumbnail': thumb_url,
            'description': self._html_search_meta('description', page),
            'creator': oembed_obj['author_name'],
            'duration': oembed_obj['duration'],
            'timestamp': creation_timestamp,
            'view_count': views,
        }


class CamdemyFolderIE(InfoExtractor):
    _VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
    _TESTS = [{
        # links with trailing slash
        'url': 'http://www.camdemy.com/folder/450',
        'info_dict': {
            'id': '450',
            'title': '信號與系統 2012 & 2011 (Signals and Systems)',
        },
        'playlist_mincount': 145
    }, {
        # links without trailing slash
        # and multi-page
        'url': 'http://www.camdemy.com/folder/853',
        'info_dict': {
            'id': '853',
            'title': '科學計算 - 使用 Matlab'
        },
        'playlist_mincount': 20
    }, {
        # with displayMode parameter. For testing the codes to add parameters
        'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
        'info_dict': {
            'id': '853',
            'title': '科學計算 - 使用 Matlab'
        },
        'playlist_mincount': 20
    }]

    def _real_extract(self, url):
        folder_id = self._match_id(url)

        # Add displayMode=list so that all links are displayed in a single page
        parsed_url = list(compat_urllib_parse.urlparse(url))
        query = dict(compat_urllib_parse.parse_qsl(parsed_url[4]))
        query.update({'displayMode': 'list'})
        parsed_url[4] = compat_urllib_parse.urlencode(query)
        final_url = compat_urllib_parse.urlunparse(parsed_url)

        page = self._download_webpage(final_url, folder_id)
        matches = re.findall(r"href='(/media/\d+/?)'", page)

        entries = [self.url_result('http://www.camdemy.com' + media_path)
                   for media_path in matches]

        folder_title = self._html_search_meta('keywords', page)

        return self.playlist_result(entries, folder_id, folder_title)