-# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
-
-import urllib2
-import xml.etree.ElementTree as ET
-import re
+from ..utils import parse_duration
class DHMIE(InfoExtractor):
- _VALID_URL = r'http://www\.dhm\.de/filmarchiv/(?P<id>.*?)'
+ IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
+ _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': {
- 'id': 'marshallwg',
+ 'id': 'the-marshallplan-at-work-in-west-germany',
'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
- 'thumbnail': 'http://www.dhm.de/filmarchiv/video/mpworkwg.jpg',
- }
- }
+ '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):
- video_id = ''
- webpage = self._download_webpage(url, video_id)
+ playlist_id = self._match_id(url)
- title = self._html_search_regex(
- r'dc:title=\"(.*?)\"', webpage, 'title')
+ webpage = self._download_webpage(url, playlist_id)
- playlist_url = self._html_search_regex(
- r'file: \'(.*?)\'', webpage, 'playlist URL')
+ playlist_url = self._search_regex(
+ r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
- xml_file = urllib2.urlopen(playlist_url)
- data = xml_file.read()
- xml_file.close()
+ entries = self._extract_xspf_playlist(playlist_url, playlist_id)
- root = ET.fromstring(data)
- video_url = root[0][0][0].text
- thumbnail = root[0][0][2].text
+ title = self._search_regex(
+ [r'dc:title="([^"]+)"', r'<title> »([^<]+)</title>'],
+ webpage, 'title').strip()
+ description = self._html_search_regex(
+ r'<p><strong>Description:</strong>(.+?)</p>',
+ webpage, 'description', default=None)
+ duration = parse_duration(self._search_regex(
+ r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
+ webpage, 'duration', default=None))
- m = re.search('video/(.+?).flv', video_url)
- if m:
- video_id = m.group(1)
-
- return {
- 'id': video_id,
+ entries[0].update({
'title': title,
- 'url': video_url,
- 'thumbnail': thumbnail,
- }
+ 'description': description,
+ 'duration': duration,
+ })
+
+ return self.playlist_result(entries, playlist_id)