import urllib.request
import re
def saveFile(path, data):
f_obj = open(path, 'wb')
f_obj.write(data)
f_obj.close()
def getData(weburl):
webheaders = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req = urllib.request.Request(url=weburl, headers=webheaders)
response = urllib.request.urlopen(req)
return response.read()
source = ['taobao', r'https://www.taobao.com/']
page = getData(source[1])
# saveFile('e:\\temp.out', page)
match = re.findall(r'((http:|https:)?//[^\s\"\&]*?(jpg|png|gif|webp))', str(page))
matchIndex = [0, 2]
for index, link in enumerate(match):
print(link)
destLink = link[matchIndex[0]]
if destLink.startswith('//'):
destLink = "http:" + destLink;
print(str(index) + " " + destLink)
try:
path = r"E:/worm_pic/" + source[0] + "/" + str(index) + '.' + link[matchIndex[1]]
print(path)
urllib.request.urlretrieve(destLink, path)
except Exception as e:
print('失败' + e.message)
import re
def saveFile(path, data):
f_obj = open(path, 'wb')
f_obj.write(data)
f_obj.close()
def getData(weburl):
webheaders = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req = urllib.request.Request(url=weburl, headers=webheaders)
response = urllib.request.urlopen(req)
return response.read()
source = ['taobao', r'https://www.taobao.com/']
page = getData(source[1])
# saveFile('e:\\temp.out', page)
match = re.findall(r'((http:|https:)?//[^\s\"\&]*?(jpg|png|gif|webp))', str(page))
matchIndex = [0, 2]
for index, link in enumerate(match):
print(link)
destLink = link[matchIndex[0]]
if destLink.startswith('//'):
destLink = "http:" + destLink;
print(str(index) + " " + destLink)
try:
path = r"E:/worm_pic/" + source[0] + "/" + str(index) + '.' + link[matchIndex[1]]
print(path)
urllib.request.urlretrieve(destLink, path)
except Exception as e:
print('失败' + e.message)