抓取几条URL后就没反应了，怎么回事
#coding:utf-8
import urllib2
class HtmlDownloader(object):
def download(self, url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
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("<head><meta charset='utf-8'></head>")
fout.write('<table>')
# ascii in python
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()
from bs4 import BeautifulSoup
import re
import urlparse
class HtmlParser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()
#/view/123.htm
links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
for link in links:
new_url = link['href']
new_full_url = urlparse.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" label-module="lemmaSummary">
summary_node = soup.find('div', class_="lemma-summary")
res_data['summary'] = summary_node.get_text()
return res_data
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
class UrlManager(object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self,url):
if url is None:
print 'no new url'
return
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
def add_new_urls(self, urls):
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_url(url)
def has_new_url(self):
return len(self.new_urls) != 0
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
class SpiderMain(object):
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.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.collect_data(new_data)
if count == 20:
break
except:
print 'craw failed'
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)我把数量设为20，运行了几次，每次抓取的条数都不一样，有两次是成功爬取20条的
以下是测试结果
==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm craw 5 : http://baike.baidu.com/view/32571.htm craw 6 : http://baike.baidu.com/view/757238.htm craw 7 : http://baike.baidu.com/view/2888099.htm craw 8 : http://baike.baidu.com/view/1369367.htm craw 9 : http://baike.baidu.com/view/737.htm craw 10 : http://baike.baidu.com/view/38648.htm craw 11 : http://baike.baidu.com/view/230750.htm craw 12 : http://baike.baidu.com/view/560583.htm craw 13 : http://baike.baidu.com/view/902.htm craw 14 : http://baike.baidu.com/view/18979.htm craw 15 : http://baike.baidu.com/view/1158766.htm craw 16 : http://baike.baidu.com/view/7977.htm craw 17 : http://baike.baidu.com/view/1298929.htm craw 18 : http://baike.baidu.com/view/642401.htm craw 19 : http://baike.baidu.com/view/52940.htm craw 20 : http://baike.baidu.com/view/449909.htm >>> ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm craw 5 : http://baike.baidu.com/view/32571.htm craw 6 : http://baike.baidu.com/view/757238.htm craw 7 : http://baike.baidu.com/view/2888099.htm craw 8 : http://baike.baidu.com/view/1369367.htm craw 9 : http://baike.baidu.com/view/737.htm craw 10 : http://baike.baidu.com/view/38648.htm craw 11 : http://baike.baidu.com/view/230750.htm craw 12 : http://baike.baidu.com/view/560583.htm craw 13 : http://baike.baidu.com/view/902.htm craw 14 : http://baike.baidu.com/view/18979.htm craw 15 : http://baike.baidu.com/view/1158766.htm craw 16 : http://baike.baidu.com/view/7977.htm craw 17 : http://baike.baidu.com/view/1298929.htm craw 18 : http://baike.baidu.com/view/642401.htm craw 19 : http://baike.baidu.com/view/52940.htm craw 20 : http://baike.baidu.com/view/449909.htm >>> ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm craw 5 : http://baike.baidu.com/view/32571.htm craw 6 : http://baike.baidu.com/view/757238.htm craw 7 : http://baike.baidu.com/view/2888099.htm craw 8 : http://baike.baidu.com/view/1369367.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm craw 5 : http://baike.baidu.com/view/32571.htm craw 6 : http://baike.baidu.com/view/757238.htm craw 7 : http://baike.baidu.com/view/2888099.htm craw 8 : http://baike.baidu.com/view/1369367.htm craw 9 : http://baike.baidu.com/view/737.htm craw 10 : http://baike.baidu.com/view/38648.htm craw 11 : http://baike.baidu.com/view/230750.htm craw 12 : http://baike.baidu.com/view/560583.htm craw 13 : http://baike.baidu.com/view/902.htm craw 14 : http://baike.baidu.com/view/18979.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm craw 3 : http://baike.baidu.com/view/53557.htm craw 4 : http://baike.baidu.com/view/10812277.htm craw 5 : http://baike.baidu.com/view/32571.htm craw 6 : http://baike.baidu.com/view/757238.htm craw 7 : http://baike.baidu.com/view/2888099.htm craw 8 : http://baike.baidu.com/view/1369367.htm craw 9 : http://baike.baidu.com/view/737.htm ==================== RESTART: G:/Python/crawler_baidu.py ==================== craw 1 : http://baike.baidu.com/view/21087.htm craw 2 : http://baike.baidu.com/view/16068.htm
