#coding=gbk
#download pictures of the url
#useage: python downpicture.py www.baidu.com
import os
import sys
from html.parser import HTMLParser
from urllib.request import urlopen
from urllib.parse import urlparse
def getpicname(path):
''' retrive filename of url '''
if os.path.splitext(path)[1] == '':
return None
pr=urlparse(path)
path='http://'+pr[1]+pr[2]
return os.path.split(path)[1]
def saveimgto(path, urls):
'''
save img of url to local path
'''
if not os.path.isdir(path):
print('path is invalid')
sys.exit()
else:
for url in urls:
of=open(os.path.join(path, getpicname(url)), 'w+b')
q=urlopen(url)
of.write(q.read())
q.close()
of.close()
class myhtmlparser(HTMLParser):
'''put all src of img into urls'''
def __init__(self):
HTMLParser.__init__(self)
self.urls=list()
self.num=0
def handle_starttag(self, tag, attr):
if tag.lower() == 'img':
srcs=[u[1] for u in attr if u[0].lower() == 'src']
self.urls.extend(srcs)
self.num = self.num+1
if __name__ == '__main__':
url=sys.argv[1]
if not url.startswith('http://'):
url='http://' + sys.argv[1]
parseresult=urlparse(url)
domain='http://' + parseresult[1]
q=urlopen(url)
content=q.read().decode('utf-8', 'ignore')
q.close()
myparser=myhtmlparser()
myparser.feed(content)
for u in myparser.urls:
if (u.startswith('//')):
myparser.urls[myparser.urls.index(u)]= 'http:'+u
elif u.startswith('/'):
myparser.urls[myparser.urls.index(u)]= domain+u
saveimgto(r'D:\python\song', myparser.urls)
print('num of download pictures is {}'.format(myparser.num))
result：
num of download pictures is 19