main_program.py 文件源码

def craw(self,lock,count):
        while 1:
            next_task=self.task.get()
            if next_task is None:
                self.task.task_done()
                continue
            # print(self.urls.new_urls)
            # new_url = self.urls.get_new_url()
            # print("%s craw %d : %s" % (multiprocessing.current_process().name,count, new_url))
            # new_html = self.downloader.download(new_url)
            # new_urls, new_data = self.parser.parse(new_url, new_html)
            # self.urls.add_new_urls(new_urls)
            # self.outputer.collect_data(new_data)
            # self.outputer.output_html()
            # count += 1
            new_url = next_task.a
            print("%s craw %d : %s" % (multiprocessing.current_process().name, count, new_url))
            new_html = self.downloader.download(new_url)
            new_urls, new_data = self.parser.parse(new_url, new_html)
            for i in range(len(new_urls)):
                self.task.put(Task(new_urls[i]))
            self.outputer.collect_data(new_data)
            self.outputer.output_html()
            self.task.task_done()
            count += 1