]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/googleplus.py
6 from .common
import InfoExtractor
12 class GooglePlusIE(InfoExtractor
):
13 """Information extractor for plus.google.com."""
15 _VALID_URL
= r
'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
16 IE_NAME
= u
'plus.google'
18 u
"url": u
"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
19 u
"file": u
"ZButuJc6CtH.flv",
21 u
"upload_date": u
"20120613",
22 u
"uploader": u
"井上ヨシマサ",
27 def _real_extract(self
, url
):
29 mobj
= re
.match(self
._VALID
_URL
, url
)
31 raise ExtractorError(u
'Invalid URL: %s' % url
)
33 post_url
= mobj
.group(0)
34 video_id
= mobj
.group(1)
36 video_extension
= 'flv'
38 # Step 1, Retrieve post webpage to extract further information
39 webpage
= self
._download
_webpage
(post_url
, video_id
, u
'Downloading entry webpage')
41 self
.report_extraction(video_id
)
44 upload_date
= self
._html
_search
_regex
('title="Timestamp">(.*?)</a>',
45 webpage
, u
'upload date', fatal
=False)
47 # Convert timestring to a format suitable for filename
48 upload_date
= datetime
.datetime
.strptime(upload_date
, "%Y-%m-%d")
49 upload_date
= upload_date
.strftime('%Y%m%d')
52 uploader
= self
._html
_search
_regex
(r
'rel\="author".*?>(.*?)</a>',
53 webpage
, u
'uploader', fatal
=False)
56 # Get the first line for title
57 video_title
= self
._html
_search
_regex
(r
'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
58 webpage
, 'title', default
=u
'NA')
60 # Step 2, Simulate clicking the image box to launch video
61 DOMAIN
= 'https://plus.google.com'
62 video_page
= self
._search
_regex
(r
'<a href="((?:%s)?/photos/.*?)"' % re
.escape(DOMAIN
),
63 webpage
, u
'video page URL')
64 if not video_page
.startswith(DOMAIN
):
65 video_page
= DOMAIN
+ video_page
67 webpage
= self
._download
_webpage
(video_page
, video_id
, u
'Downloading video page')
69 # Extract video links on video page
70 """Extract video links of all sizes"""
71 pattern
= r
'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
72 mobj
= re
.findall(pattern
, webpage
)
74 raise ExtractorError(u
'Unable to extract video links')
79 # Choose the lowest of the sort, i.e. highest resolution
81 # Only get the url. The resolution part in the tuple has no use anymore
82 video_url
= video_url
[-1]
83 # Treat escaped \u0026 style hex
85 video_url
= video_url
.decode("unicode_escape")
86 except AttributeError: # Python 3
87 video_url
= bytes(video_url
, 'ascii').decode('unicode-escape')
94 'upload_date': upload_date
,
96 'ext': video_extension
,