靜態頁面的抓取(學習簡單爬蟲)
阿新 • • 發佈:2019-02-09
聖誕節快樂(づ ̄ 3 ̄)づ~~~
在這個半放假的日子裡,人也變得慵懶起來,在MOOC下學習了靜態頁面的簡單爬蟲(傳送門:http://www.imooc.com/learn/563),乾貨滿滿啊~~
所以爬了一個羋月傳麼麼噠~~~
# coding=utf-8
import urllib2
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
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()
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={}
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()
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 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("<meta charset='UTF-8'>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
fout.write("<tr>")
#asci
fout.write("<td>%s</td>"% data['url'])
fout.write("<td>%s</td>"% data['title'].encode('utf-8'))
print data['title'].encode('utf-8')
fout.write("<td>%s</td>"% data['summary'].encode('utf-8'))
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
fout.close()
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==50:
break
count = count +1
except:
print 'craw failed'
self.outputer.output_html()
if __name__=="__main__":
root_url="http://baike.baidu.com/subview/9975572/10764629.htm"
obj_spider= SpiderMain()
obj_spider.craw(root_url)
有些小的細節沒有做好,所以在除錯上費了不少的功夫,還是太粗心了T^T
需要說明的一點是,跟著老師的程式碼,當寫入到output.html中出現了亂碼,但是寫到output.txt中不會有問題。查了一下是因為html頁面如果是中文也需要進行編碼的說明,因此在原來程式碼基礎上增加了
fout.write("<meta charset='UTF-8'>")
開心地去看羋月傳啦~~~~