Python get_links_from_html_body示例

示例#1

文件： zerochan_html.py 项目： simon987/chan_feed

 def item_urls(self, item, board):
     return [
         x for x in set(
             get_links_from_html_body(item["html"], self._base_url))
         if "google.com" not in x and "whatanime.ga" not in x
         and "iqdb.org" not in x and "saucenao.com" not in x
     ]

示例#2

 def item_urls(self, item, board):
     return [
         url for url in set(
             get_links_from_html_body(
                 item["html"],
                 self._base_url.replace("<sub>", self._subdomain(board))))
         if "javascript" not in url
     ]

示例#3

文件： endchan_html.py 项目： worst/chan_feed

 def item_urls(self, item, board):
     return list(set(get_links_from_html_body(item["html"],
                                              self._base_url)))