aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/xuite.py
blob: a9dbf8c2de1e5c5c8ca75793eeb86450c825381c (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
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

import base64

from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
    ExtractorError,
    parse_iso8601,
    parse_duration,
)


class XuiteIE(InfoExtractor):
    _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
    _VALID_URL = r'http://vlog.xuite.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
    _TESTS = [{
        # Audio
        'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
        'md5': '63a42c705772aa53fd4c1a0027f86adf',
        'info_dict': {
            'id': '3860914',
            'ext': 'mp3',
            'title': '孤單南半球-歐德陽',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 247.246,
            'timestamp': 1314932940,
            'upload_date': '20110902',
            'uploader': '阿能',
            'uploader_id': '15973816',
            'categories': ['個人短片'],
        },
    }, {
        # Video with only one format
        'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2',
        'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e',
        'info_dict': {
            'id': '3441629',
            'ext': 'mp4',
            'title': '孫燕姿 - 眼淚成詩',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 217.399,
            'timestamp': 1299383640,
            'upload_date': '20110306',
            'uploader': 'Valen',
            'uploader_id': '10400126',
            'categories': ['影視娛樂'],
        },
    }, {
        # Video with two formats
        'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
        'md5': '1166e0f461efe55b62e26a2d2a68e6de',
        'info_dict': {
            'id': '21301170',
            'ext': 'mp4',
            'title': '暗殺教室 02',
            'description': '字幕:【極影字幕社】',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 1384.907,
            'timestamp': 1421481240,
            'upload_date': '20150117',
            'uploader': '我只是想認真點',
            'uploader_id': '242127761',
            'categories': ['電玩動漫'],
        },
    }, {
        'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
        'only_matching': True,
    }]

    def _extract_flv_config(self, media_id):
        base64_media_id = base64.b64encode(media_id.encode('utf-8')).decode('utf-8')
        flv_config = self._download_xml(
            'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
            'flv config')
        prop_dict = {}
        for prop in flv_config.findall('./property'):
            prop_id = base64.b64decode(prop.attrib['id']).decode('utf-8')
            # CDATA may be empty in flv config
            if not prop.text:
                continue
            encoded_content = base64.b64decode(prop.text).decode('utf-8')
            prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
        return prop_dict

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

        webpage = self._download_webpage(url, video_id)

        error_msg = self._search_regex(
            r'<div id="error-message-content">([^<]+)',
            webpage, 'error message', default=None)
        if error_msg:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, error_msg),
                expected=True)

        video_id = self._html_search_regex(
            r'data-mediaid="(\d+)"', webpage, 'media id')
        flv_config = self._extract_flv_config(video_id)

        FORMATS = {
            'audio': 'mp3',
            'video': 'mp4',
        }

        formats = []
        for format_tag in ('src', 'hq_src'):
            video_url = flv_config.get(format_tag)
            if not video_url:
                continue
            format_id = self._search_regex(
                r'\bq=(.+?)\b', video_url, 'format id', default=format_tag)
            formats.append({
                'url': video_url,
                'ext': FORMATS.get(flv_config['type'], 'mp4'),
                'format_id': format_id,
                'height': int(format_id) if format_id.isnumeric() else None,
            })
        self._sort_formats(formats)

        timestamp = flv_config.get('publish_datetime')
        if timestamp:
            timestamp = parse_iso8601(timestamp + ' +0800', ' ')

        category = flv_config.get('category')
        categories = [category] if category else []

        return {
            'id': video_id,
            'title': flv_config['title'],
            'description': flv_config.get('description'),
            'thumbnail': flv_config.get('thumb'),
            'timestamp': timestamp,
            'uploader': flv_config.get('author_name'),
            'uploader_id': flv_config.get('author_id'),
            'duration': parse_duration(flv_config.get('duration')),
            'categories': categories,
            'formats': formats,
        }