# coding=gbk
'''
Created on 2017年11月23日
@author: stu
'''
from baike_spider import url_manager, html_downloader, html_parser,\
html_outputer
# 初始化url管理器、下载器、解析器、输出器
class SpiderMain(object):
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_outputer.HtmlOutputer()
def craw(self,root_url):
count = 1
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
print ("craw %d : %s" %(count,new_url))
html_cont = self.downloader.download(new_url)
new_urls, new_data = self.parser.parse(new_url,html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.callect_data(new_data)
if count ==100:
break
count += 1
except:
print('craw failed')
self.outputer.output_html()
if __name__ =='__main__':
root_url = "https://baike.baidu.com/item/Python/407313?fr=aladdin"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
Traceback (most recent call last):
File "D:\eclipse\workspase\imooc\src\baike_spider\spider_main.py", line 45, in <module>
obj_spider.craw(root_url)
File "D:\eclipse\workspase\imooc\src\baike_spider\spider_main.py", line 23, in craw
self.urls.add_new_url(root_url)
TypeError: add_new_url() takes 1 positional argument but 2 were given
添加回答
举报
0/150
提交
取消