正则表达式爬虫1

正则表达式小例子

import re
li='hellonihaohello'
a=re.search(r'\Ahello',li)
print a.group()
b=re.search(r'hello\Z',li)
print b.group()
li='i have a dream'
c=re.search(r'\bhave\b',li)
print c.group() 
content = 'i have a [email protected] dream one day ... [email protected] money neau'
data=re.findall(r'\d{6,11}@qq\.com',content)
print data

使用正则表达式爬取糗事百科图片

"""
通过正则表达式，下载糗事百科图片
"""
import requests
import re
#设置下载网页的页面url
url='https://www.qiushibaike.com/imgrank/'

#设置请求头数据
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
}
#发送请求
response=requests.get(url,headers=headers)
#解析数据
html=response.content.decode('utf8')
#print html
# with io.open('d:/python/pachong/jiandan.txt','w',encoding='utf8') as f:
#     f.write(html)


#通过正则表达式获取我们需要的数据
reStr='<img src="/{1,2}[^(static)](.*?)"'
data=re.findall(reStr,html)
#print data
for item in data:
    if not item.startswith("http:"):
        item="http://"+item
    print item

    response = requests.get(item)
    data=response.content
    nameList=item.split("/")
    imageName=nameList[len(nameList)-1]
    a=re.search('.*(jpg)$',imageName)
    if(a!=None):
        print imageName
        with io.open('d:/python/pachong/'+imageName,'wb') as f:
            f.write(data)