def catch(source_url):
curr_url, html = loadPage(source_url)
# 解析
# 判断内容解析方式
content_item = parseContent(curr_url, html)
content_item_common = CommonParse.parse(html) or {}
content_item = content_item or {}
title = content_item.get(u'title') or content_item_common.get(
u'title') or u''
post_date = content_item.get(u'post_date') or content_item_common.get(
u'post_date') or u''
content_html = content_item.get(
u'content_html') or content_item_common.get(u'content_html') or u''
if not title and not post_date and not content_html:
return -100, u'没有抓取到相关内容', None
else:
# 得到最终的结果
styles = u''
if content_html:
# styles = operateCss(content_item, content_item_common, html)
content_html = downLoadImg(source_url, content_html)
# 去除 image 的 alt title
content_html = clearAltTitleHref(content_html)
# 去除不要的标签内容
clear_paths_in = content_item.get(
u'clear_paths_in') or content_item_common.get(
u'clear_paths_in') or []
clearPaths = [u'//script'] + clear_paths_in
content_html = clearDOM(content_html, clearPaths)
# 处理时间
post_date = DateUtil.dateFormat(dateStr=post_date)
return upload_result(title, post_date, content_html, styles)
