Python bulk download image of Mowgli and Hummingbird pictures crawler Small application

Some redundant information, because the regular expressions were tested before, so they are not removed, but do not affect the use.

#-*-Coding:utf-8-*-import re,urllib,sys,os,timedef getallurl (): entry=sys.argv[1] #try: Getpage=urllib.urlopen ( Entry). Read () #except: #print "Error" Pattern=re.compile (R ' <a href= "(. +?)". +?> ') Web_site_pattern=re.compile (R ' (http:.+?) ') All_url = Pattern.findall (getpage) for URLs in All_url:if web_site_pattern.match (URLs):p rint url#print urlprint "Done" def Download_pic (): url=sys.argv[1]; #local_path = "c:/tools/source/" Connection=urllib.urlopen (URL) data= Connection.read () print "Waiting to get Data" Time.sleep (3) connection.close () #analyze #p =re.compile (R ' img width= "\d+". +src= "(. +)". + ') Download_pic_pattern=re.compile (R '  ') #p10 =re.compile (R ' (. +) \.jpg ' ) All_url=download_pic_pattern.findall (data) #print all_urli=1directory= "C:/tools/source" Name_pattern=re.compile ( R '/(\w+?\.jpg) ') if not os.path.exists (directory): Os.mkdir (directory) for URLs in All_url:print urls#print "Working" # Print Local_pathi=i+1name=name_pattern.findall (URLs) print name[0]local_path= "c:/tools/source/%s" % name[0] Jpeg_connection=urllib.urlopen (URLs) jpeg=jpeg_connection.read () time.sleep (1) print "Waiting" f=file (local _path, "WB") f.write (JPEG) f.close () jpeg_connection.close () #i =i+1#f=file (Local_path, "WB") #f. Write (data) #f. Close () Print ("Done") def download_pic_2 (): url=sys.argv[1];local_path= "C:/tools/a.jpg" Data=urllib.urlretrieve (Url,local_ Path) print ("Done") def Regulation (): str1= "abc123*gbk1024abc*defb1kc12*addd" P1=re.compile (R ' abc ') Print P1.findall ( STR1) P2=re.compile (R ' a.c ') print P2.findall (str1) p3=re.compile (R ' abc\* ') print P3.findall (str1) p4=re.compile (R ' [ Abc]12 ') print P4.findall (str1) p5=re.compile (R ' \d\* ') print P5.findall (str1) p6=re.compile (R ' a[^\d] ') print P6.findall (STR1) p7=re.compile (R ' a[^\d]* ') print P7.findall (str1) p8=re.compile (R ' [a-za-z]+ (\d+) ') Print P8.findall ( STR1) str2= "Dadfae ef  Asdfe aa<ima" p9=re.compile (R ')  ') Urls=p9.findall (str2) #printprint urlsfor URL in urls:print urlif __name__ = = "__maIn__ ": #main () #download_pic_2 () #regulation () Download_pic () #getAllUrl () 

Python bulk download image of Mowgli and Hummingbird pictures crawler Small application