]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/googledrive.py
37be34091895392b014a8fe2167d9c708ca60e71
[youtubedl] / youtube_dl / extractor / googledrive.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 ExtractorError,
8 int_or_none,
9 )
10
11
12 class GoogleDriveIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
14 _TEST = {
15 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
16 'md5': '881f7700aec4f538571fa1e0eed4a7b6',
17 'info_dict': {
18 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
19 'ext': 'mp4',
20 'title': 'Big Buck Bunny.mp4',
21 'duration': 46,
22 }
23 }
24 _FORMATS_EXT = {
25 '5': 'flv',
26 '6': 'flv',
27 '13': '3gp',
28 '17': '3gp',
29 '18': 'mp4',
30 '22': 'mp4',
31 '34': 'flv',
32 '35': 'flv',
33 '36': '3gp',
34 '37': 'mp4',
35 '38': 'mp4',
36 '43': 'webm',
37 '44': 'webm',
38 '45': 'webm',
39 '46': 'webm',
40 '59': 'mp4',
41 }
42
43 @staticmethod
44 def _extract_url(webpage):
45 mobj = re.search(
46 r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
47 webpage)
48 if mobj:
49 return 'https://drive.google.com/file/d/%s' % mobj.group('id')
50
51 def _real_extract(self, url):
52 video_id = self._match_id(url)
53 webpage = self._download_webpage(
54 'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
55
56 reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
57 if reason:
58 raise ExtractorError(reason)
59
60 title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
61 duration = int_or_none(self._search_regex(
62 r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
63 fmt_stream_map = self._search_regex(
64 r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
65 fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
66
67 formats = []
68 for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
69 fmt_id, fmt_url = fmt_stream.split('|')
70 resolution = fmt.split('/')[1]
71 width, height = resolution.split('x')
72 formats.append({
73 'url': fmt_url,
74 'format_id': fmt_id,
75 'resolution': resolution,
76 'width': int_or_none(width),
77 'height': int_or_none(height),
78 'ext': self._FORMATS_EXT[fmt_id],
79 })
80 self._sort_formats(formats)
81
82 return {
83 'id': video_id,
84 'title': title,
85 'thumbnail': self._og_search_thumbnail(webpage, default=None),
86 'duration': duration,
87 'formats': formats,
88 }