R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Safer extraction

Browse Source
This commit is contained in:
AlexAplin 2018-06-15 17:20:37 -04:00
parent d26a533272
commit cdde4e4764
1 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube_dl/extractor/iwara.py
View File

@ -85,19 +85,26 @@ class IwaraIE(InfoExtractor):
upload_date = unified_strdate(self._html_search_regex( upload_date = unified_strdate(self._html_search_regex(
r'作成日:(\d{4}-\d{2}-\d{2})', webpage, 'upload_date', fatal=False)) r'作成日:(\d{4}-\d{2}-\d{2})', webpage, 'upload_date', fatal=False))
uploader = get_element_by_class('username', webpage) node_info_class = get_element_by_class('node-info', webpage)
if node_info_class is not None:
uploader = self._html_search_regex(
r'<a.*title="ユーザー (.+) の写真[^>]+', node_info_class, 'uploader', fatal=False)
description = clean_html(get_element_by_class('field-type-text-with-summary', webpage)) description = clean_html(get_element_by_class('field-type-text-with-summary', webpage))
comments_id = get_element_by_id('comments', webpage) comments_id = get_element_by_id('comments', webpage)
comment_count = int_or_none(self._html_search_regex( if comments_id is not None:
r'([\d,]+)', get_element_by_class('title', comments_id), 'comment_count', fatal=False)) comments_header = get_element_by_class('title', comments_id)
if comments_header is not None:
comment_count = int_or_none(self._html_search_regex(
r'([\d,]+)', get_element_by_class('title', comments_id), 'comment_count', fatal=False))
node_views_class = get_element_by_class('node-views', webpage) node_views_class = get_element_by_class('node-views', webpage)
like_count = str_to_int(self._html_search_regex( if node_views_class is not None:
r'glyphicon-heart[^>]+><\/i>\s+([\d,]+)', node_views_class, 'like_count', fatal=False)) like_count = str_to_int(self._html_search_regex(
view_count = str_to_int(self._html_search_regex( r'glyphicon-heart[^>]+></i>\s+([\d,]+)', node_views_class, 'like_count', fatal=False))
r'glyphicon-eye-open[^>]+><\/i>\s+([\d,]+)', node_views_class, 'view_count', fatal=False)) view_count = str_to_int(self._html_search_regex(
r'glyphicon-eye-open[^>]+></i>\s+([\d,]+)', node_views_class, 'view_count', fatal=False))
formats = [] formats = []
for a_format in video_data: for a_format in video_data: