You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlp/youtube_dl/extractor/dhm.py

74 lines
2.4 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
10 years ago
from ..utils import (
xpath_text,
parse_duration,
)
class DHMIE(InfoExtractor):
10 years ago
IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
_VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': {
10 years ago
'id': 'the-marshallplan-at-work-in-west-germany',
'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
10 years ago
'description': 'md5:1fabd480c153f97b07add61c44407c82',
'duration': 660,
'thumbnail': 're:^https?://.*\.jpg$',
},
}, {
'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
'md5': '09890226332476a3e3f6f2cb74734aa5',
'info_dict': {
'id': 'rolle-1',
'ext': 'flv',
'title': 'ROLLE 1',
'thumbnail': 're:^https?://.*\.jpg$',
},
}]
def _real_extract(self, url):
10 years ago
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
10 years ago
playlist_url = self._search_regex(
r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
10 years ago
playlist = self._download_xml(playlist_url, video_id)
10 years ago
track = playlist.find(
'./{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
10 years ago
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')
10 years ago
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', default=None)
10 years ago
duration = parse_duration(self._search_regex(
r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
webpage, 'duration', default=None))
return {
'id': video_id,
'url': video_url,
10 years ago
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
}