[wayofthemaster] Add extractor (Fixes #3575)

This commit is contained in:
Philipp Hagemeister 2014-08-24 03:44:54 +02:00
parent f56f8399c7
commit e5402ac120
2 changed files with 54 additions and 0 deletions

View file

@ -390,6 +390,7 @@ from .vuclip import VuClipIE
from .vulture import VultureIE from .vulture import VultureIE
from .washingtonpost import WashingtonPostIE from .washingtonpost import WashingtonPostIE
from .wat import WatIE from .wat import WatIE
from .wayofthemaster import WayOfTheMasterIE
from .wdr import ( from .wdr import (
WDRIE, WDRIE,
WDRMobileIE, WDRMobileIE,

View file

@ -0,0 +1,53 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import determine_ext
class WayOfTheMasterIE(InfoExtractor):
_VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])'
_TEST = {
'url': 'http://www.wayofthemaster.com/hbks.shtml',
'md5': '5316b57487ada8480606a93cb3d18d24',
'info_dict': {
'id': 'hbks',
'ext': 'mp4',
'title': 'Intelligent Design vs. Evolution',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._search_regex(
r'<img src="images/title_[^"]+".*?alt="([^"]+)"',
webpage, 'title', default=None)
if title is None:
title = self._html_search_regex(
r'<title>(.*?)</title>', webpage, 'page title')
url_base = self._search_regex(
r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"',
webpage, 'URL base')
formats = [{
'format_id': 'low',
'quality': 1,
'url': url_base + '_low.mp4',
}, {
'format_id': 'high',
'quality': 2,
'url': url_base + '_high.mp4',
}]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
}