ytdl-nightly/youtube_dl/extractor/dhm.py

65 lines
2.1 KiB
Python
Raw Normal View History

2015-03-28 10:38:52 +01:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-03-28 17:30:13 +01:00
from ..utils import (
xpath_text,
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'
_VALID_URL = r'http://www\.dhm\.de/filmarchiv/die-filme/(?P<id>[^/]+)'
2015-03-28 10:38:52 +01:00
_TEST = {
'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': 're:^https?://.*\.jpg$',
2015-03-28 10:38:52 +01:00
}
}
def _real_extract(self, url):
2015-03-28 17:30:13 +01:00
video_id = self._match_id(url)
2015-03-28 10:38:52 +01:00
webpage = self._download_webpage(url, video_id)
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
2015-03-28 17:30:13 +01:00
playlist = self._download_xml(playlist_url, video_id)
2015-03-28 10:38:52 +01:00
2015-03-28 17:30:13 +01:00
track = playlist.find(
'./{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
2015-03-28 10:38:52 +01:00
2015-03-28 17:30:13 +01:00
video_url = xpath_text(
track, './{http://xspf.org/ns/0/}location',
'video url', fatal=True)
thumbnail = xpath_text(
track, './{http://xspf.org/ns/0/}image',
'thumbnail')
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>',
webpage, 'description', fatal=False)
duration = parse_duration(self._search_regex(
r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
webpage, 'duration', fatal=False))
2015-03-28 10:38:52 +01:00
return {
'id': video_id,
'url': video_url,
2015-03-28 17:30:13 +01:00
'title': title,
'description': description,
'duration': duration,
2015-03-28 10:38:52 +01:00
'thumbnail': thumbnail,
}