最后只能爬取到第一个
# coding:utf8
from baike import url_manager, html_downloader, html_parser, html_outputer
class SpiderMain(object):
def __init__(self):
self.urls = url_manager.UrlManager() #URL管理器
self.downloader = html_downloader.HtmlDownloader() #Html下载器
self.parser = html_parser.HtmlParser() #html解析器
self.outputer = html_outputer.HtmlOutputer()
def craw(self,root_url):
count = 1
self.urls.add_new_url(root_url) #添加入口URL
#当有新的URL时
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url() #从urls获取新的url
print 'craw %d : %s' %(count,new_url) #打印craw+count：新的url
html_cont = self.downloader.download(new_url) #下载url界面
new_urls, new_data = self.parser.parse(new_url, html_cont) #解析下载界面
self.urls.add_new_urls(new_urls) #添加批量的url
self.outputer.collect_data(new_data) #收集新数据
if count == 1000:
break
count = 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)
class UrlManager(object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
#添加单个url
def add_new_url(self, url):
if url is None:
return
#如果是全新的URL
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
#添加批量的URLS
def add_new_urls(self, urls):
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_url(url)
#判断列表中是否有未爬取过的url
def has_new_url(self):
return len(self.new_urls) != 0
#获取新的URL
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
# coding:utf8
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()
import re
import urlparse
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',herf = 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 = {}
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
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'].encode('utf-8'))
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()
