python爬虫_入门_翻页

#!/usr/bin/python
# coding: UTF-8

import urllib
import urllib2
import re

#处理地址，并获取页面全部的图片地址
def get_image_url(url):
  #url_format = urllib2.Request(url) #1
  url_open = urllib.urlopen(url) #2
  url_read = url_open.read() #3
  re_value = re.compile(‘(?<=src\=\").*?\.jpg‘)
  image_url_list = re.findall(re_value,url_read) #4
  return image_url_list

#这个函数专门用来下载，前面两行是将图片连接中/前面的内容全部删除，留下后面的文件名用来保存文件的，try不说了，不清楚请翻回去看容错
def down_image(image_url):
  rev = ‘^.*/‘
  file_name = re.sub(rev,‘‘,image_url)
  try:
    urllib.urlretrieve(image_url,file_name)
  except:
    print ‘download %s fail‘ %image_url
  else:
    print ‘download %s successed‘ %image_url

#这个函数用来处理页面，每次+1
def get_page(url):
  url_num = re.search(‘(?<=\/)[0-9]+(?=\.)‘,url)
  url_num = url_num.group()
  url_num_1 = int(url_num) + 1
  url = url.replace(url_num,str(url_num_1))
  return url

if __name__ == ‘__main__‘:
  url = ‘http://bbs.fengniao.com/forum/10384633.html‘
  for n in range(1,10):
    url = get_page(url)
    image_url_list = get_image_url(url)
    for image_url in image_url_list:
      down_image(image_url) #5