]>
Commit | Line | Data |
---|---|---|
0c56a3f7 | 1 | # coding: utf-8 |
3501423d | 2 | from __future__ import unicode_literals |
0c56a3f7 | 3 | |
7aca14a1 | 4 | import re |
4828703f | 5 | import codecs |
7aca14a1 PH |
6 | |
7 | from .common import InfoExtractor | |
4828703f | 8 | from ..utils import unified_strdate |
7aca14a1 PH |
9 | |
10 | ||
11 | class GooglePlusIE(InfoExtractor): | |
3501423d JMF |
12 | IE_DESC = 'Google Plus' |
13 | _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)' | |
14 | IE_NAME = 'plus.google' | |
0c56a3f7 | 15 | _TEST = { |
3501423d JMF |
16 | 'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH', |
17 | 'info_dict': { | |
18 | 'id': 'ZButuJc6CtH', | |
19 | 'ext': 'flv', | |
4828703f | 20 | 'title': '嘆きの天使 降臨', |
3501423d JMF |
21 | 'upload_date': '20120613', |
22 | 'uploader': '井上ヨシマサ', | |
0c56a3f7 PH |
23 | } |
24 | } | |
7aca14a1 PH |
25 | |
26 | def _real_extract(self, url): | |
4828703f | 27 | video_id = self._match_id(url) |
7aca14a1 PH |
28 | |
29 | # Step 1, Retrieve post webpage to extract further information | |
3501423d | 30 | webpage = self._download_webpage(url, video_id, 'Downloading entry webpage') |
7aca14a1 | 31 | |
4828703f S |
32 | title = self._og_search_description(webpage).splitlines()[0] |
33 | upload_date = unified_strdate(self._html_search_regex( | |
685a9cd2 | 34 | r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*> |
e94b783c | 35 | ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''', |
4828703f S |
36 | webpage, 'upload date', fatal=False, flags=re.VERBOSE)) |
37 | uploader = self._html_search_regex( | |
38 | r'rel="author".*?>(.*?)</a>', webpage, 'uploader', fatal=False) | |
7aca14a1 | 39 | |
d6628960 | 40 | # Step 2, Simulate clicking the image box to launch video |
7f3c4f4f | 41 | DOMAIN = 'https://plus.google.com/' |
4828703f S |
42 | video_page = self._search_regex( |
43 | r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN), | |
3501423d | 44 | webpage, 'video page URL') |
d6628960 PH |
45 | if not video_page.startswith(DOMAIN): |
46 | video_page = DOMAIN + video_page | |
47 | ||
3501423d | 48 | webpage = self._download_webpage(video_page, video_id, 'Downloading video page') |
7aca14a1 | 49 | |
4828703f S |
50 | def unicode_escape(s): |
51 | decoder = codecs.getdecoder('unicode_escape') | |
52 | return re.sub( | |
53 | r'\\u[0-9a-fA-F]{4,}', | |
54 | lambda m: decoder(m.group(0))[0], | |
55 | s) | |
7aca14a1 | 56 | |
4828703f S |
57 | # Extract video links all sizes |
58 | formats = [{ | |
59 | 'url': unicode_escape(video_url), | |
60 | 'ext': 'flv', | |
61 | 'width': int(width), | |
62 | 'height': int(height), | |
63 | } for width, height, video_url in re.findall( | |
64 | r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)] | |
65 | self._sort_formats(formats) | |
7aca14a1 | 66 | |
3501423d JMF |
67 | return { |
68 | 'id': video_id, | |
4828703f | 69 | 'title': title, |
7aca14a1 | 70 | 'uploader': uploader, |
3501423d | 71 | 'upload_date': upload_date, |
4828703f | 72 | 'formats': formats, |
3501423d | 73 | } |