Use Python to download pictures of Sister map sites

Recently in the reptile section of learning Python. See a netizen in sharing the use of crawler crawling all kinds of Web site's code, also want to write a play. Today took the time to analyze the structure of the sister map and HTML code, using URLLIB2 and BeautifulSoup wrote a automatic download pictures of the sister image of the script.

Sister Figure website: http://www.mzitu.com

The results are as follows:

650) this.width=650; "src=" http://s3.51cto.com/wyfs02/M00/6D/BE/wKiom1VqxezQ2gI5AAIsE59qMbE377.jpg "style=" float: none; "title=" 1.png "alt=" Wkiom1vqxezq2gi5aaise59qmbe377.jpg "/>

650) this.width=650; "src=" http://s3.51cto.com/wyfs02/M01/6D/BA/wKioL1Vqx4PxV3a7AAE-zNgCpXY813.jpg "style=" float: none; "title=" 2.png "alt=" Wkiol1vqx4pxv3a7aae-zngcpxy813.jpg "/>

The source code is as follows, please the Great God teach you:

# -*- coding:utf8 -*-# python:         2.7.8#  Platform:       Windows# Author:          wucl# version:        1.0# program:          automatically download pictures of sister images and save to local # history:         2015.5.31import urllib2, os, os.path, urllibfrom bs4 import  beautifulsoupdef get_pages (URL):     "" "     get the number of pages in the sister chart site       "" "        html=urllib2.urlopen (URL). Read ()      soup=beautifulsoup (HTML)     nums=soup.find_all (' A ', class_= ' page-numbers ' )     pages=int (Nums[-2].text)     return pages     def get_menU (URL):     "" "     get the link name and address of all sister chart themes for the page, enter the list     " "     html=urllib2.urlopen (URL). Read ()     soup=beautifulsoup (HTML)      menu=[]    menu_list=soup.find_all (' A ', target= ' _blank ')      for i in menu_list:        result=i.find_ All (' img ', class_= ' lazy ')         if result:             name=result[0][' Alt ']             address=i[' href ']             menu.append ([name,address])     return menudef get_links ( URL):     "" "     get a single sister chart topic total number of pictures     " "     html=urllib2.urLopen (URL). Read ()     soup=beautifulsoup (HTML)     all_=soup.find_all (' A ')     nums=[]    for i in all_:         span=i.find_all (' span ')         if span:             nums.append (Span[0].text)      return nums[-2]            def  get_image (url,filename):     "" "     extract pictures from a separate page save as filename      "" "    html=urllib2.urlopen (URL). Read ()     soup= BeautifulSoup (HTML)     image=soup.find_all (' P ') [0].find_all (' img ') [0][' src ']     urllib.urlretrieve (image,filename) def main (page):     "" "      download page of the sister figure &NBsp;    ""     print u ' downloading page  %d  '  % page     page_url=url+ '/page/' +str (page)     menu=get_menu (page_url)      print u '  %d  page total  %d  theme '  % (Page,len (menu))      For i in menu:        dir_name=os.path.join (' MeiZiTu ', I [0])         if not os.path.exists (Dir_name):             os.mkdir (Dir_name)          pic_nums=int (Get_links (i[1))         print u ' theme   %s  altogether has  %d  picture '  % (i[0],pic_nums)         for  Pic in range (1,pic_nums+1):             Basename=str (pic) + '. JPG '             filename=os.path.join (Dir_name, basename)             pic_url=i[1]+ '/' +str (pic)             if not os.path.exists ( FileName):                 Print u ' ........ You are downloading  %s '  % basename                 get_image (Pic_url,filename)              else:                 print filename+u ' already exists, skipped '     if __name__== ' __main__ ':     url= ' http://www.mzitu.com/'     pages=get_pages (URL)      Print u ' sister figure there are &Nbsp;%d  page '  %pages    if not os.path.exists (' MeiZiTu '):         os.mkdir (' Meizitu ')     page_start=input (U ') Enter the start page of the sister graph: \ n ')     page_end=input (U ' Enter the end page of the sister graph: \ n ')     if page_end>page_ Start:        for page in range (page_start,page_end):             main (page)     elif  page_end==page_start:        main (page_end)      else:        print u "input error, start Page must be less than or equal to end page \ n"

This article is from the "Wine similarities Lake" blog, please be sure to keep this source http://wucl202000.blog.51cto.com/4687508/1656871

Use Python to download pictures of Sister map sites