]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/promptfile.py
[brightcove:new] extract subtitles and strip video title
[youtube-dl] / youtube_dl / extractor / promptfile.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8     determine_ext,
9     ExtractorError,
10     sanitized_Request,
11     urlencode_postdata,
12 )
13
14
15 class PromptFileIE(InfoExtractor):
16     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
17     _TEST = {
18         'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
19         'md5': 'd1451b6302da7215485837aaea882c4c',
20         'info_dict': {
21             'id': 'D21B4746E9-F01462F0FF',
22             'ext': 'mp4',
23             'title': 'Birds.mp4',
24             'thumbnail': 're:^https?://.*\.jpg$',
25         }
26     }
27
28     def _real_extract(self, url):
29         video_id = self._match_id(url)
30         webpage = self._download_webpage(url, video_id)
31
32         if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
33             raise ExtractorError('Video %s does not exist' % video_id,
34                                  expected=True)
35
36         fields = self._hidden_inputs(webpage)
37         post = urlencode_postdata(fields)
38         req = sanitized_Request(url, post)
39         req.add_header('Content-type', 'application/x-www-form-urlencoded')
40         webpage = self._download_webpage(
41             req, video_id, 'Downloading video page')
42
43         url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
44         title = self._html_search_regex(
45             r'<span.+title="([^"]+)">', webpage, 'title')
46         thumbnail = self._html_search_regex(
47             r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
48             webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
49
50         formats = [{
51             'format_id': 'sd',
52             'url': url,
53             'ext': determine_ext(title),
54         }]
55         self._sort_formats(formats)
56
57         return {
58             'id': video_id,
59             'title': title,
60             'thumbnail': thumbnail,
61             'formats': formats,
62         }