mirrors/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[motherless] Simplify

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-10-24 19:53:48 +02:00
parent 7f9ced64cb
commit 8efd06aa42
1 changed files with 20 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/motherless.py
View File

@ -5,7 +5,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, str_to_int,
unified_strdate, unified_strdate,
) )
@ -57,30 +57,34 @@ class MotherlessIE(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('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') title = self._html_search_regex(
r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') video_url = self._html_search_regex(
r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
view_count = str_to_int(self._html_search_regex(
r'<strong>Views</strong>\s+([^<]+)<',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex(
r'<strong>Favorited</strong>\s+([^<]+)<',
webpage, 'like count', fatal=False))
view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count') upload_date = self._html_search_regex(
r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date')
if 'Ago' in upload_date: if 'Ago' in upload_date:
days = int(re.search(r'([0-9]+)', upload_date).group(1)) days = int(re.search(r'([0-9]+)', upload_date).group(1))
upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
else: else:
upload_date = unified_strdate(upload_date) upload_date = unified_strdate(upload_date)
like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count')
comment_count = webpage.count('class="media-comment-contents"') comment_count = webpage.count('class="media-comment-contents"')
uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id') uploader_id = self._html_search_regex(
r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
webpage, 'uploader_id')
categories = self._html_search_meta('keywords', webpage) categories = self._html_search_meta('keywords', webpage)
if categories: if categories:
@ -93,8 +97,8 @@ class MotherlessIE(InfoExtractor):
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'categories': categories, 'categories': categories,
'view_count': int_or_none(view_count.replace(',', '')), 'view_count': view_count,
'like_count': int_or_none(like_count.replace(',', '')), 'like_count': like_count,
'comment_count': comment_count, 'comment_count': comment_count,
'age_limit': age_limit, 'age_limit': age_limit,
'url': video_url, 'url': video_url,