def url_extrator(self,response): # 从href提取URL队列并加入到target_url中
try:
iter_url = regex.URL_REGEX.finditer(response) # href="/b/a"
filter_data = Filter(iter_url,"url",self.requests_seen) # 初始化过滤器
target_queue = filter_data.extractor(self.logger_type,self.target) # 提取到除特殊文件之外的URL队列
self.target_url.put(target_queue)
except Exception:
pass
def url_extrator(self,response):
try:
iter_url = regex.URL_REGEX.finditer(response)
filter_data = Filter(iter_url,"url",self.requests_seen)
target_queue = filter_data.extractor(self.logger_type,self.target)
self.target_url.put(target_queue)
except Exception:
pass
