Use Python3 to write a script for capturing webpages and only webpage images,

Use Python3 to write a script for capturing webpages and only webpage images,

The most basic code implementation for capturing webpage content:

#!/usr/bin/env python  from urllib import urlretrieve  def firstNonBlank(lines):   for eachLine in lines:     if not eachLine.strip():       continue     else:       return eachLine  def firstLast(webpage):   f = open(webpage)   lines = f.readlines()   f.close()   print firstNonBlank(lines),   lines.reverse()   print firstNonBlank(lines),  def download(url='http://www',process=firstLast):   try:     retval = urlretrieve(url)[0]   except IOError:     retval = None   if retval:     process(retval)  if __name__ == '__main__':   download() 

The urllib module is used to capture images on a webpage:

import urllib.request import socket import re import sys import os targetDir = r"C:\Users\elqstux\Desktop\pic" def destFile(path):   if not os.path.isdir(targetDir):     os.mkdir(targetDir)   pos = path.rindex('/')   t = os.path.join(targetDir, path[pos+1:])   return t  if __name__ == "__main__":   hostname = "http://www.douban.com"   req = urllib.request.Request(hostname)   webpage = urllib.request.urlopen(req)   contentBytes = webpage.read()   for link, t in set(re.findall(r'(http:[^\s]*?(jpg|png|gif))', str(contentBytes))):     print(link)     urllib.request.urlretrieve(link, destFile(link)) 

Import urllib. request import socket import re import sys import OS targetDir = r "H: \ pic" def destFile (path): if not OS. path. isdir (targetDir): OS. mkdir (targetDir) pos = path. rindex ('/') t = OS. path. join (targetDir, path [pos + 1:]) # return t if _ name _ = "_ main _" separated __": hostname = "http://www.douban.com/" req = urllib. request. request (hostname) webpage = urllib. request. urlopen (req) contentBytes = w Ebpage. read () match = re. findall (R' (http: [^ \ s] *? (Jpg | png | gif) ', str (contentBytes) # R' (http: [^ \ s] *? (Jpg | png | gif) 'contains two parentheses, so there are two groups. # The list is returned, and the matching content in the brackets appears in the list for picname, picType in match: print (picname) print (picType) ''' output: http://img3.douban.com/pics/blank.gif gif http://img3.douban.com/icon/g111328-1.jpg. jpg http://img3.douban.com/pics/blank.gif. gif http://img3.douban.com/icon/g197523-19.jpg. gif... '''