该python脚本主要是实现以上功能。
其中,使用beautifulsoup来解析html,可以参考我的另外一篇文章:windows8下安装beautifulsoup
代码如下:
复制代码 代码如下:
__author__ = '曾是土木人'
# -*- coding: utf-8 -*-
#采集serp搜索结果标题
import urllib2
from bs4 import beautifulsoup
import time
#写文件
def writefile(filename,content):
try:
fp = file(filename,a+)
fp.write(content + \r)
fp.close()
except:
pass#获取html源码
def gethtml(url):
try:
req = urllib2.request(url)
response= urllib2.urlopen(req,none,3)#设置超时时间
data = response.read().decode('utf-8','ignore')
except:pass
return data
#提取搜索结果serp的标题
def fetchtitle(html):
try:
soup = beautifulsoup(''.join(html))
for i in soup.findall(h3):
title = i.text.encode(utf-8)
if any(str_ in title for str_ in (北京,厦门)):
continue
else:
print title
writefile(result.txt,title)
except:
pass
keyword = 58同城
if __name__ == __main__:
global keyword
start = time.time()
for i in range(0,8):
url = http://www.baidu.com/s?wd=intitle:+keyword+&rn=100&pn=+str(i*100)
html = gethtml(url)
fetchtitle(html)
time.sleep(1)
c = time.time() - start
print('程序运行耗时:%0.2f 秒'%(c))
