youtube-dl/youtube_dl/extractor/dhm.py

60 lines
2.0 KiB
Python
Raw Permalink Normal View History

2015-03-28 10:38:52 +01:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-08-12 21:19:23 +02:00
from ..utils import parse_duration
2015-03-28 10:38:52 +01:00
class DHMIE(InfoExtractor):
2015-03-28 17:30:13 +01:00
IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
2015-03-28 18:55:15 +01:00
_VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
2015-03-28 10:38:52 +01:00
2015-03-28 18:55:15 +01:00
_TESTS = [{
2015-03-28 10:38:52 +01:00
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': {
2015-03-28 17:30:13 +01:00
'id': 'the-marshallplan-at-work-in-west-germany',
2015-03-28 10:38:52 +01:00
'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
2015-03-28 17:30:13 +01:00
'description': 'md5:1fabd480c153f97b07add61c44407c82',
'duration': 660,
'thumbnail': r're:^https?://.*\.jpg$',
2015-03-28 18:55:15 +01:00
},
}, {
'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
'md5': '09890226332476a3e3f6f2cb74734aa5',
'info_dict': {
'id': 'rolle-1',
'ext': 'flv',
'title': 'ROLLE 1',
'thumbnail': r're:^https?://.*\.jpg$',
2015-03-28 18:55:15 +01:00
},
}]
2015-03-28 10:38:52 +01:00
def _real_extract(self, url):
2015-08-09 15:21:25 +02:00
playlist_id = self._match_id(url)
2015-03-28 17:30:13 +01:00
2015-08-09 15:21:25 +02:00
webpage = self._download_webpage(url, playlist_id)
2015-03-28 10:38:52 +01:00
2015-03-28 17:30:13 +01:00
playlist_url = self._search_regex(
r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
2015-03-28 10:38:52 +01:00
2015-08-09 15:21:25 +02:00
entries = self._extract_xspf_playlist(playlist_url, playlist_id)
2015-03-28 10:38:52 +01:00
2015-03-28 17:30:13 +01:00
title = self._search_regex(
[r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
webpage, 'title').strip()
description = self._html_search_regex(
r'<p><strong>Description:</strong>(.+?)</p>',
2015-03-28 18:55:15 +01:00
webpage, 'description', default=None)
2015-03-28 17:30:13 +01:00
duration = parse_duration(self._search_regex(
r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
2015-03-28 18:55:15 +01:00
webpage, 'duration', default=None))
2015-03-28 10:38:52 +01:00
2015-08-09 15:21:25 +02:00
entries[0].update({
2015-03-28 17:30:13 +01:00
'title': title,
'description': description,
'duration': duration,
2015-08-09 15:21:25 +02:00
})
return self.playlist_result(entries, playlist_id)