]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xuite.py
Prepare new release.
[youtubedl] / youtube_dl / extractor / xuite.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import base64
5
6 from .common import InfoExtractor
7 from ..compat import compat_urllib_parse_unquote
8 from ..utils import (
9 ExtractorError,
10 parse_iso8601,
11 parse_duration,
12 )
13
14
15 class XuiteIE(InfoExtractor):
16 IE_DESC = '隨意窩Xuite影音'
17 _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
18 _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
19 _TESTS = [{
20 # Audio
21 'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
22 'md5': 'e79284c87b371424885448d11f6398c8',
23 'info_dict': {
24 'id': '3860914',
25 'ext': 'mp3',
26 'title': '孤單南半球-歐德陽',
27 'thumbnail': r're:^https?://.*\.jpg$',
28 'duration': 247.246,
29 'timestamp': 1314932940,
30 'upload_date': '20110902',
31 'uploader': '阿能',
32 'uploader_id': '15973816',
33 'categories': ['個人短片'],
34 },
35 }, {
36 # Video with only one format
37 'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
38 'md5': '21f7b39c009b5a4615b4463df6eb7a46',
39 'info_dict': {
40 'id': '25925099',
41 'ext': 'mp4',
42 'title': 'BigBuckBunny_320x180',
43 'thumbnail': r're:^https?://.*\.jpg$',
44 'duration': 596.458,
45 'timestamp': 1454242500,
46 'upload_date': '20160131',
47 'uploader': 'yan12125',
48 'uploader_id': '12158353',
49 'categories': ['個人短片'],
50 'description': 'http://download.blender.org/peach/bigbuckbunny_movies/BigBuckBunny_320x180.mp4',
51 },
52 }, {
53 # Video with two formats
54 'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
55 'md5': '1166e0f461efe55b62e26a2d2a68e6de',
56 'info_dict': {
57 'id': '21301170',
58 'ext': 'mp4',
59 'title': '暗殺教室 02',
60 'description': '字幕:【極影字幕社】',
61 'thumbnail': r're:^https?://.*\.jpg$',
62 'duration': 1384.907,
63 'timestamp': 1421481240,
64 'upload_date': '20150117',
65 'uploader': '我只是想認真點',
66 'uploader_id': '242127761',
67 'categories': ['電玩動漫'],
68 },
69 'skip': 'Video removed',
70 }, {
71 # Video with encoded media id
72 # from http://forgetfulbc.blogspot.com/2016/06/date.html
73 'url': 'http://vlog.xuite.net/embed/cE1xbENoLTI3NDQ3MzM2LmZsdg==?ar=0&as=0',
74 'info_dict': {
75 'id': 'cE1xbENoLTI3NDQ3MzM2LmZsdg==',
76 'ext': 'mp4',
77 'title': '男女平權只是口號?專家解釋約會時男生是否該幫女生付錢 (中字)',
78 'description': 'md5:f0abdcb69df300f522a5442ef3146f2a',
79 'timestamp': 1466160960,
80 'upload_date': '20160617',
81 'uploader': 'B.C. & Lowy',
82 'uploader_id': '232279340',
83 },
84 }, {
85 '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',
86 'only_matching': True,
87 }]
88
89 @staticmethod
90 def base64_decode_utf8(data):
91 return base64.b64decode(data.encode('utf-8')).decode('utf-8')
92
93 @staticmethod
94 def base64_encode_utf8(data):
95 return base64.b64encode(data.encode('utf-8')).decode('utf-8')
96
97 def _extract_flv_config(self, encoded_media_id):
98 flv_config = self._download_xml(
99 'http://vlog.xuite.net/flash/player?media=%s' % encoded_media_id,
100 'flv config')
101 prop_dict = {}
102 for prop in flv_config.findall('./property'):
103 prop_id = self.base64_decode_utf8(prop.attrib['id'])
104 # CDATA may be empty in flv config
105 if not prop.text:
106 continue
107 encoded_content = self.base64_decode_utf8(prop.text)
108 prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
109 return prop_dict
110
111 def _real_extract(self, url):
112 video_id = self._match_id(url)
113
114 webpage = self._download_webpage(url, video_id)
115
116 error_msg = self._search_regex(
117 r'<div id="error-message-content">([^<]+)',
118 webpage, 'error message', default=None)
119 if error_msg:
120 raise ExtractorError(
121 '%s returned error: %s' % (self.IE_NAME, error_msg),
122 expected=True)
123
124 encoded_media_id = self._search_regex(
125 r'attributes\.name\s*=\s*"([^"]+)"', webpage,
126 'encoded media id', default=None)
127 if encoded_media_id is None:
128 video_id = self._html_search_regex(
129 r'data-mediaid="(\d+)"', webpage, 'media id')
130 encoded_media_id = self.base64_encode_utf8(video_id)
131 flv_config = self._extract_flv_config(encoded_media_id)
132
133 FORMATS = {
134 'audio': 'mp3',
135 'video': 'mp4',
136 }
137
138 formats = []
139 for format_tag in ('src', 'hq_src'):
140 video_url = flv_config.get(format_tag)
141 if not video_url:
142 continue
143 format_id = self._search_regex(
144 r'\bq=(.+?)\b', video_url, 'format id', default=format_tag)
145 formats.append({
146 'url': video_url,
147 'ext': FORMATS.get(flv_config['type'], 'mp4'),
148 'format_id': format_id,
149 'height': int(format_id) if format_id.isnumeric() else None,
150 })
151 self._sort_formats(formats)
152
153 timestamp = flv_config.get('publish_datetime')
154 if timestamp:
155 timestamp = parse_iso8601(timestamp + ' +0800', ' ')
156
157 category = flv_config.get('category')
158 categories = [category] if category else []
159
160 return {
161 'id': video_id,
162 'title': flv_config['title'],
163 'description': flv_config.get('description'),
164 'thumbnail': flv_config.get('thumb'),
165 'timestamp': timestamp,
166 'uploader': flv_config.get('author_name'),
167 'uploader_id': flv_config.get('author_id'),
168 'duration': parse_duration(flv_config.get('duration')),
169 'categories': categories,
170 'formats': formats,
171 }