Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 09:10:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

[dhm] Simplify

Browse Source
This commit is contained in:
Sergey M․ 2015-03-28 22:30:13 +06:00
parent 79fd11ab8e
commit af8c93086c
1 changed files with 35 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
youtube_dl/extractor/dhm.py
View File

@ -1,53 +1,64 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
import urllib2 xpath_text,
import xml.etree.ElementTree as ET parse_duration,
import re )
class DHMIE(InfoExtractor): class DHMIE(InfoExtractor):
IE_DESC = 'Deutsches Historisches Museum' IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
_VALID_URL = r'http://www\.dhm\.de/filmarchiv/(?P<id>.*?)' _VALID_URL = r'http://www\.dhm\.de/filmarchiv/die-filme/(?P<id>[^/]+)'
_TEST = { _TEST = {
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/', 'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827', 'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': { 'info_dict': {
'id': 'marshallwg', 'id': 'the-marshallplan-at-work-in-west-germany',
'ext': 'flv', 'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE', '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$',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = '' video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex( playlist_url = self._search_regex(
r'dc:title=\"(.*?)\"', webpage, 'title') r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
playlist_url = self._html_search_regex( playlist = self._download_xml(playlist_url, video_id)
r'file: \'(.*?)\'', webpage, 'playlist URL')
xml_file = urllib2.urlopen(playlist_url) track = playlist.find(
data = xml_file.read() './{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
xml_file.close()
root = ET.fromstring(data) video_url = xpath_text(
video_url = root[0][0][0].text track, './{http://xspf.org/ns/0/}location',
thumbnail = root[0][0][2].text 'video url', fatal=True)
thumbnail = xpath_text(
track, './{http://xspf.org/ns/0/}image',
'thumbnail')
m = re.search('video/(.+?).flv', video_url) title = self._search_regex(
if m: [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
video_id = m.group(1) 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))
return { return {
'id': video_id, 'id': video_id,
'title': title,
'url': video_url, 'url': video_url,
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }