[normalboots] Modernize

This commit is contained in:
Philipp Hagemeister 2015-02-02 23:04:39 +01:00
parent 3a4cca687f
commit 531572578e
1 changed files with 14 additions and 11 deletions

View File

@ -11,7 +11,7 @@ from ..utils import (
class NormalbootsIE(InfoExtractor): class NormalbootsIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$' _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
_TEST = { _TEST = {
'url': 'http://normalboots.com/video/home-alone-games-jontron/', 'url': 'http://normalboots.com/video/home-alone-games-jontron/',
'md5': '8bf6de238915dd501105b44ef5f1e0f6', 'md5': '8bf6de238915dd501105b44ef5f1e0f6',
@ -30,19 +30,22 @@ class NormalbootsIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('videoid')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
webpage, 'uploader')
raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
webpage, 'date')
video_upload_date = unified_strdate(raw_upload_date)
player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url') video_uploader = self._html_search_regex(
r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
webpage, 'uploader', fatal=False)
video_upload_date = unified_strdate(self._html_search_regex(
r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
webpage, 'date', fatal=False))
player_url = self._html_search_regex(
r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"',
webpage, 'player url')
player_page = self._download_webpage(player_url, video_id) player_page = self._download_webpage(player_url, video_id)
video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file') video_url = self._html_search_regex(
r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
return { return {
'id': video_id, 'id': video_id,