SoFunction
Updated on 2024-11-19

python crawl web page image example (python crawler)


#-*- encoding: utf-8 -*-
'''
Created on 2014-4-24

@author: Leon Wong
'''

import urllib2
import urllib
import re
import time
import os
import uuid

# Get secondary page url
def findUrl2(html):
    re1 = r'/\d+/\d+/|http://\w+(?<!photos)./\d+/'
    url2list = (re1,html)
    url2lstfltr = list(set(url2list))
    (key=)
    #print url2lstfltr
    return url2lstfltr

# Get html text
def getHtml(url):
html = (url).read().decode('utf-8')# decode to utf-8
    return html

#Download images locally
def download(html_page , pageNo):  
#Define the name of the folder
    x = (())
    foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
    re2=r'/.+/f/.+\.jpg'
    imglist=(re2,html_page)
    print imglist
    download_img=None
    for imgurl in imglist:
        picpath = 'D:\\TuChong\\%s\\%s'  % (foldername,str(pageNo))
        filename = str(uuid.uuid1())
        if not (picpath):
            (picpath)              
        target = picpath+"\\%" % filename
        print "The photos location is:"+target
download_img = (imgurl, target)# download the image to the specified path
        (1)
        print(imgurl)
    return download_img


# def callback(blocknum, blocksize, totalsize):
# '''Callback function'''
# @blocknum: blocks already downloaded
# @blocksize: size of the data block
# @totalsize: size of the remote file
#     '''
#     print str(blocknum),str(blocksize),str(totalsize)
#     if blocknum * blocksize >= totalsize:
# print 'download complete'

def quitit():
    print "Bye!"
    exit(0)
   

if __name__ == '__main__':
    print '''            *****************************************
            **    Welcome to Spider for TUCHONG    **
            **      Created on 2014-4-24           **
            **      @author: Leon Wong             **
            *****************************************'''
    pageNo = raw_input("Input the page number you want to scratch (1-100),please input 'quit' if you want to quit>")
    while not () or int(pageNo) > 100 :
        if pageNo == 'quit':quitit()
        print "Param is invalid , please try again."
        pageNo = raw_input("Input the page number you want to scratch >")

#Crawl against the Tupelo Portrait Module
    html = getHtml("/tags/%E4%BA%BA%E5%83%8F/?page="+str(pageNo))

    detllst = findUrl2(html)
    for detail in detllst:
        html2 = getHtml(detail)
        download(html2,pageNo)
    print "Finished."