Use python to crawl small images to meet your desires (crawlers ),

Use python to crawl small images to meet your desires (crawlers ),

import requests
import re
import os,sys

links=[]
titles=[]

headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}

Def get_url (page ):
Url = 'HTTP: // www.zbjuran.com/mei/xinggan/list_13_developers.html'% (page)
Data = requests. get (url, headers = headers). text
Data_use = re. findall ('<div class = "name"> <a target = "_ blank" href = ".*? "Title = ".*? </A> </div> ', data)
For use in data_use:
Link = 'HTTP: // www.zbjuran.com/'{use.split ('href = "') [1]. split ('" title') [0]
Links. append (link)
Title = use. split ('title = "') [1]. split ('"> ') [0]
Titles. append (title)
Mkpath = '/Users/b1ancheng/mzpc/% s' % title
Wtxtpath = '/Users/b1ancheng/mzpc/% s/%s.txt' % (title, title)
Def get_pic ():

Url_data = requests. get (link). text
Page = int (url_data.split ('<div class = "page"> <li> <a> col') [1]. split (' page: ') [0])
For I in range (1, page + 1 ):
Print ('downloading Page % s' % I)
Pic_url = (link [:-5] + '_ % s' + link [-5:]) % I
Print (pic_url)
Try:
Pic_data_link = 'HTTP: // www.zbjuran.com '+ requests. get (pic_url, headers = headers, timeout = 5 ). text. split (' </div>') [0]
With open ('/Users/b1ancheng/mzpc/% s _ % s. JPG' % (title, title, I), 'wb') as pic_download:
Pic_download.write (requests. get (pic_data_link). content)
Failed t Exception as error:
Print (error)
Continue
# Creating a directory
IsExists = OS. path. exists (mkpath)
If not isExists:
OS. makedirs (mkpath)
Get_pic ()
Else:
Return False
If _ name _ = '_ main __':
For page in range (1, 88 ):
Get_url (page)