1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-22 22:47:55 +01:00

[DHM] Add new extractor

This commit is contained in:
Oskar Jauch 2015-03-28 10:38:52 +01:00
parent 4747e2183a
commit 643fe72717
2 changed files with 53 additions and 0 deletions

View File

@ -106,6 +106,7 @@ from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .dreisat import DreiSatIE

View File

@ -0,0 +1,52 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import urllib2
import xml.etree.ElementTree as ET
import re
class DHMIE(InfoExtractor):
_VALID_URL = r'http://www\.dhm\.de/filmarchiv/(?P<id>.*?)'
_TEST = {
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': {
'id': 'marshallwg',
'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
'thumbnail': 'http://www.dhm.de/filmarchiv/video/mpworkwg.jpg',
}
}
def _real_extract(self, url):
video_id = ''
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'dc:title=\"(.*?)\"', webpage, 'title')
playlist_url = self._html_search_regex(
r'file: \'(.*?)\'', webpage, 'playlist URL')
xml_file = urllib2.urlopen(playlist_url)
data = xml_file.read()
xml_file.close()
root = ET.fromstring(data)
video_url = root[0][0][0].text
thumbnail = root[0][0][2].text
m = re.search('video/(.+?).flv', video_url)
if m:
video_id = m.group(1)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
}