                        课程
                    
                        /后端开发
                        
                            /Python
                        
                        /Python开发简单爬虫

python新手，程序比对了n遍，没问题啊结果网址出现乱码

调度器

#coding:utf-8
from baike_spiter import url_manger, html_download, html_paser, html_outputer
class Spitermain(object):
#初始化爬虫
def __init__(self):
# url管理器
self.urls = url_manger.UrlManger()
# 下载器
self.downloader = html_download.HtmlDownload()
# 解析器
self.parser = html_paser.HtmlPaser()
# 输出器
self.outputer = html_outputer.HtmlOutputer()

# craw方法表示爬虫的调度程序
def craw(self, root_url):
count = 1
# 将入口url添加进url管理器
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 == 10:
break
count = count + 1
except:
print "craw failed"
self.outputer.output_html()

if __name__=="__main__":
root_url = "http://baike.baidu.com/item/Python"
obj_spiter = Spitermain()
obj_spiter.craw(root_url)

url管理器

#encoding=utf-8
class UrlManger(object):
def __init__(self):
self.new_urls=set() #待爬的url集合
self.old_urls=set() #已经爬取的url集合

def add_new_url(self,url):
if url is None:
return
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
return
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() #获取url，并从集合中剔除url
self.old_urls.add(new_url)
return new_url

下载器

import urllib2

class HtmlDownload(object):
def download(self,url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()

#coding:utf-8
import urlparse
import bs4
import re

解析器
class HtmlPaser(object):
def parse(self, page_url, html_cont):
if page_url is None or html_cont is None:
return
soup = bs4.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):
# 新的带爬取的url集合
new_urls=set()
#/view/123.htm
links=soup.find_all('a',href=re.compile(r"/item/"))
for link in links:
new_url=link['href']
#urljoin 的作用是将newurl按照page-url 的格式创建全新的url
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
输出器
class HtmlOutputer(object):
def __init__(self):
self.datas=[]
def collect_data(self, new_data):
if data is None:
return
self.datas.append(new_data)

def output_html(self):
fout=open("output.html",'w',encoding='utf-8')
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>")