Python网络爬虫笔记（一）：网页抓取方式和LXML示例

 1 import urllib.request as re
 2 import lxml.html
 3 #下载网页并返回HTML
 4 def download(url,user_agent='Socrates',num=2):
 5     print('下载:'+url)
 6     #设置用户代理
 7     headers = {'user_agent':user_agent}
 8     request = re.Request(url,headers=headers)
 9     try:
10         #下载网页
11         html = re.urlopen(request).read()
12     except re.URLError as e:
13         print('下载失败'+e.reason)
14         html=None
15         if num>0:
16             #遇到5XX错误时，递归调用自身重试下载，最多重复2次
17             if hasattr(e,'code') and 500<=e.code<600:
18                 return download(url,num=num-1)
19     return html
20 html = download('https://tieba.baidu.com/p/5475267611')
21 #将HTML解析为统一的格式
22 tree = lxml.html.fromstring(html)
23 # img = tree.cssselect('img.BDE_Image')
24 #通过lxml的xpath获取src属性的值，返回一个列表
25 img = tree.xpath('//img[@class="BDE_Image"]/@src')
26 x= 0
27 #迭代列表img,将图片保存在当前目录下
28 for i in img:
29     re.urlretrieve(i,'%s.jpg'%x)
30     x += 1