python网络爬虫学习笔记（1）

pip install beautifulsoup4

pip install lxml

pip install cssselect

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