lxml练习

 1 import requests
 2 from lxml import etree
 3 
 4 def loadpage(url):
 5     headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}
 6     r=requests.get(url,headers=headers)
 7     html=r.text
 8     content=etree.HTML(html)
 9     link_list=content.xpath('//div[@class="threadlist_lz clearfix"]//a/@href')
10     for link in link_list:
11         fulllink="http://tieba.baidu.com"+link
12         loadpage(fulllink)
13 
14 
15 def loadimage(link):
16     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}
17     r = requests.get(link, headers=headers)
18     html = r.text
19     content = etree.HTML(html)
20     link_list = content.xpath('//img[@class="BDE_Image"]/@src')
21     for link in link_list:
22         writeimage(link)
23 
24 def writeimage(link):
25     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}
26     r=requests.get(link,headers=headers)
27     filename=link[-5:]
28     with open(filename,'wb') as f:
29         f.write(r.text)

 

转载于:https://www.cnblogs.com/realmonkeykingsun/p/7871460.html