#coding:utf-8
"""@author 篮子里"""
from baike_spider import html_downloader,html_outputer,html_parser,url_manager
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.HtmOutputer()
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 {0}:{1}".format(count,new_url))
html_cont=self.downloader.download(new_url)
new_url,new_data=self.parser.parse(new_url,html_cont)
self.urls.add_new_url(new_url)
self.outputer.collect_data(new_data)
if count==1000:
break
count+=1
except(Exception):
print("Failed!")
self.outputer.output_html()
if __name__=="__main__":
root_url="http://baike.baidu.com/subview/16030/16030.htm"
obj_spider=SpiderMain()
obj_spider.craw(root_url)
class UrlManager(object):
def __init__(self):
self.new_urls=set()
self.old_urls=set()
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)
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
import requests
class HtmlDownloader(object):
def download(self,url):
if url is None:
return None
r=requests.get(url)
if r.status_code !=200:
return None
return r.text.decode('UTF-8')
from bs4 import BeautifulSoup
import re
import urlparse2
class HtmlParser(object):
def _get_new_urls(self,page_url,soup):
new_urls=set()
#http://www.huajiao.com/l/82485740?hd=1
links=soup.find_all("a",href=re.compile(r"/subview/\d+/\d+.htm"))
for link in links:
new_url=link["href"]
new_full_url=urlparse2.urljoin(page_url,new_url)
new_urls.add(new_full_url)
return new_url
def get_new_data(self,page_url,soup):
res_data={}
res_data["url"]=page_url
#<dd class="lemmaWgt-lemmaTitle-title"><h1>科比·布莱恩特</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_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")
new_urls = self._get_new_urls(page_url, soup)
new_data = self._get_new_data(page_url, soup)
return new_urls, new_data
class HtmOutputer(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",encoding="utf-8")
fout.write("<html>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
fout.write("<tr>")
fout.write("<td>{0}</td>".format(data["url"]))
fout.write("<td>{0}</td>".format(data["title"].encode("UTF-8")))
fout.write("<td>{0}</td>".format(data["summary"].encode("UTF-8")))
fout.write("</tr>")
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
fout.close()
二毛毛
相关分类