]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xuite.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
8 get_element_by_attribute
,
14 class XuiteIE(InfoExtractor
):
15 IE_DESC
= '隨意窩Xuite影音'
16 _REGEX_BASE64
= r
'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
17 _VALID_URL
= r
'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
20 'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
21 'md5': 'e79284c87b371424885448d11f6398c8',
26 'description': '孤單南半球-歐德陽',
27 'thumbnail': r
're:^https?://.*\.jpg$',
29 'timestamp': 1314932940,
30 'upload_date': '20110902',
32 'uploader_id': '15973816',
33 'categories': ['個人短片'],
36 # Video with only one format
37 'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
38 'md5': '21f7b39c009b5a4615b4463df6eb7a46',
42 'title': 'BigBuckBunny_320x180',
43 'thumbnail': r
're:^https?://.*\.jpg$',
45 'timestamp': 1454242500,
46 'upload_date': '20160131',
48 'uploader_id': '12158353',
49 'categories': ['個人短片'],
50 'description': 'http://download.blender.org/peach/bigbuckbunny_movies/BigBuckBunny_320x180.mp4',
53 # Video with two formats
54 'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
55 'md5': '1166e0f461efe55b62e26a2d2a68e6de',
60 'description': '字幕:【極影字幕社】',
61 'thumbnail': r
're:^https?://.*\.jpg$',
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'],
69 'skip': 'Video removed',
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',
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': 'md5:1223810fa123b179083a3aed53574706',
79 'timestamp': 1466160960,
80 'upload_date': '20160617',
81 'uploader': 'B.C. & Lowy',
82 'uploader_id': '232279340',
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,
89 def _real_extract(self
, url
):
90 # /play/ URLs provide embedded video URL and more metadata
91 url
= url
.replace('/embed/', '/play/')
92 video_id
= self
._match
_id
(url
)
94 webpage
= self
._download
_webpage
(url
, video_id
)
96 error_msg
= self
._search
_regex
(
97 r
'<div id="error-message-content">([^<]+)',
98 webpage
, 'error message', default
=None)
100 raise ExtractorError(
101 '%s returned error: %s' % (self
.IE_NAME
, error_msg
),
104 media_info
= self
._parse
_json
(self
._search
_regex
(
105 r
'var\s+mediaInfo\s*=\s*({.*});', webpage
, 'media info'), video_id
)
107 video_id
= media_info
['MEDIA_ID']
110 for key
in ('html5Url', 'html5HQUrl'):
111 video_url
= media_info
.get(key
)
114 format_id
= self
._search
_regex
(
115 r
'\bq=(.+?)\b', video_url
, 'format id', default
=None)
118 'ext': 'mp4' if format_id
.isnumeric() else format_id
,
119 'format_id': format_id
,
120 'height': int(format_id
) if format_id
.isnumeric() else None,
122 self
._sort
_formats
(formats
)
124 timestamp
= media_info
.get('PUBLISH_DATETIME')
126 timestamp
= parse_iso8601(timestamp
+ ' +0800', ' ')
128 category
= media_info
.get('catName')
129 categories
= [category
] if category
else []
131 uploader
= media_info
.get('NICKNAME')
134 author_div
= get_element_by_attribute('itemprop', 'author', webpage
)
136 uploader
= uploader
or self
._html
_search
_meta
('name', author_div
)
137 uploader_url
= self
._html
_search
_regex
(
138 r
'<link[^>]+itemprop="url"[^>]+href="([^"]+)"', author_div
,
139 'uploader URL', fatal
=False)
143 'title': media_info
['TITLE'],
144 'description': remove_end(media_info
.get('metaDesc'), ' (Xuite 影音)'),
145 'thumbnail': media_info
.get('ogImageUrl'),
146 'timestamp': timestamp
,
147 'uploader': uploader
,
148 'uploader_id': media_info
.get('MEMBER_ID'),
149 'uploader_url': uploader_url
,
150 'duration': float_or_none(media_info
.get('MEDIA_DURATION'), 1000000),
151 'categories': categories
,