[megavideozeu] Simplify (Closes #5454)

This commit is contained in:
Sergey M․ 2015-04-19 04:07:45 +06:00
parent f32cb5cb14
commit 31f224008e

View File

@ -1,51 +1,52 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, float_or_none,
parse_filesize, xpath_text,
unified_strdate,
) )
class MegavideozeuIE(InfoExtractor): class MegavideozeuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>.*)(?:.*)' _VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>[^/]+)(?:/(?P<display_id>[^/]+))?'
_TESTS = [ _TEST = {
{ 'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader', 'info_dict': {
'info_dict': { 'id': '48723',
'id': '48723', 'display_id': 'SMPTE-Universal-Film-Leader',
'ext': 'mp4', 'ext': 'mp4',
'duration': '10', 'title': 'SMPTE Universal Film Leader',
'title': 'SMPTE Universal Film Leader', 'thumbnail': 're:https?://.*?\.jpg',
} 'duration': 10.93,
} }
] }
def _real_extract(self, url): def _real_extract(self, url):
tmp_video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, tmp_video_id) webpage = self._download_webpage(url, display_id)
config_php = self._html_search_regex( config = self._download_xml(
r'var cnf = \'([^\']+)\'', webpage, 'config.php url') self._search_regex(
r"var\s+cnf\s*=\s*'([^']+)'", webpage, 'cnf url'),
display_id)
configpage = self._download_webpage(config_php, tmp_video_id) video_url = xpath_text(config, './file', 'video url', fatal=True)
title = xpath_text(config, './title', 'title', fatal=True)
video_id = self._html_search_regex( thumbnail = xpath_text(config, './image', 'thumbnail')
r'<mediaid>([^<]+)', configpage, 'video id') duration = float_or_none(xpath_text(config, './duration', 'duration'))
video_url = self._html_search_regex( video_id = xpath_text(config, './mediaid', 'video id') or video_id
r'<file>([^<]+)', configpage, 'video URL')
title = self._html_search_regex(
r'<title><!\[CDATA\[([^\]]+)', configpage, 'title')
duration = int_or_none(self._html_search_regex(
r'<duration>([0-9\.]+)', configpage, 'duration', fatal=False))
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'url': video_url, 'url': video_url,
'title': title, 'title': title,
'thumbnail': thumbnail,
'duration': duration 'duration': duration
} }