用的是pycharm，python3.5，爬取失败，求助
错误如下：
craw 1 : http://baike.baidu.com/view/21087.htm
Traceback (most recent call last):
File "D:/python/spider/spider/spider_main.py", line 36, in <module>
obj_spider.craw(root_url)
File "D:/python/spider/spider/spider_main.py", line 22, in craw
self.outputer.collect_data(new_data)
TypeError: collect_data() missing 1 required positional argument: 'data'
spider_main代码 如下：
# coding:utf-8
from spider import url_manager, html_downloader, html_parser, html_outputer
class SpiderMain(object):
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtlmDownloader()
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():
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.collect_data(new_data)
if count == 100:
break
count = count+1
self.outputer.output_html()
if __name__ == "__main__":
root_url = 'http://baike.baidu.com/view/21087.htm'
obj_spider = SpiderMain()
obj_spider.craw(root_url)
outputer 模块代码如下：
# coding:utf-8
class HtmlOutputer(object):
def __init__(self):
self.datas = []
def collect_data(self, data):
if data is None:
return
self.datas.append(data)
def output_html(self):
fout = open('output.html', 'w')
fout.write("<html>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
fout.write("<tr>")
fout.write("<td>%s</td>" % data['url'])
fout.write("<td>%s</td>" % data['title'].encode('utf-8'))
fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
fout.write("</tr>")
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
fout.close()
parser模块代码如下：
# coding:utf-8
import re
import urllib.parse
from bs4 import BeautifulSoup
class HtmlParser(object):
def parse(self, page_url, html_cont):
if page_url is None or html_cont is None:
return
soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
new_urls = self._get_new_urls(page_url, soup)
new_data = self._get_new_data(page_url, soup)
return new_urls, new_data
def _get_new_urls(self, page_url, soup):
new_urls=set()
links=soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
for link in links:
new_url=link['href']
new_full_url=urllib.parse.urljoin(page_url, new_url)
new_urls.add(new_full_url)
return new_urls
def _get_new_data(self, page_url, soup):
res_data= {}
#url
res_data['url']=page_url
#<dd class="lemmaWgt-lemmaTitle-title"> <h1>Python</h1>
title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find("h1")
res_data['title'] = title_node.get_text()
#<div class="lemma-summary">
summary_node = soup.find('div', class_="lemma-summary")
res_data['summary'] = summary_node.get_text()
return res_data
