示例#1
0
 def catch_info(self, target_url):
     content = HttpBaseClass.get_http_content(target_url, timeout=SettingClass.WAITFOR_HTML)
     if not content:
         return
     self.info_url_set.discard(target_url)
     parser = CollectionParser(content)
     self.info_list.append(parser.get_extra_info())
     return
示例#2
0
 def catch_info(self, target_url):
     content = HttpBaseClass.get_http_content(
         target_url, timeout=SettingClass.WAITFOR_HTML)
     if not content:
         return
     self.info_url_set.discard(target_url)
     parser = CollectionParser(content)
     self.info_list.append(parser.get_extra_info())
     return
示例#3
0
    def parse_content(self,content):
        parser = CollectionParser(content)
        self.question_list += parser.get_question_info_list()
        self.answer_list += parser.get_answer_list()

        collection_info = parser.get_extra_info()
        self.add_collection_index(collection_info['collection_id'], parser.get_answer_list())

        return
示例#4
0
    def parse_content(self, content):
        parser = CollectionParser(content)
        self.question_list += parser.get_question_info_list()
        self.answer_list += parser.get_answer_list()

        collection_info = parser.get_extra_info()
        self.add_collection_index(collection_info['collection_id'],
                                  parser.get_answer_list())

        return