python 抓取美女图片
# -*- coding:utf8 -*-# __author__ = 'jony'
from bs4 import BeautifulSoup
import os, sys, urllib2,time,random
import re
def GetUrl():
url = 'http://www.27270.com/ent/meinvtupian/'
header = {'User-Agent' : 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)'}
request = urllib2.Request(url,None,header)
response = urllib2.urlopen(request,None,timeout=10).read()
#pattern = re.compile(r'<a href="(.*)" title="(.*)"> class="MMPic"><i><img src="(.*)" width="190" height="280"alt=.*')#在一行无法正则获取，所以使用BeautifulSoup
soup = BeautifulSoup(response,"html.parser", from_encoding="gb18030") #WARNING:root:Some characters could not be decoded, and were replaced with REPLACEMENT CHARACTER.所以gb18030
#soup = BeautifulSoup(response,from_encoding='gb2312')
#过滤 div为MeinvTuPianBox
content = soup.find_all('div',attrs={'class':'MeinvTuPianBox'})
#定义列表
urls = []
#titles = []
#picurls = []
for i in content:
#再次过滤 MMpic 注意是a 不是div了
for j in i.findAll('a',attrs={'class':'MMPic'}):
urls.append(j.get('href'))
#titles.append(j.get('title'))
return urls
def GetImage(*urls):
header = {'User-Agent' : 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)'}
pattern = re.compile(r'<img alt=".*" src="(.*)" />')
for url in urls:
print url
#获取初始的页面的图片
try:
request = urllib2.Request(url,None,header)
response = urllib2.urlopen(request).read()
girlink = pattern.search(response).group(1)
print girlink
req = urllib2.Request(girlink,None,header)
res = urllib2.urlopen(req,None,timeout=10).read()
with open(u'PICTURE'+'/'+time.strftime('%H%M%S')+str(random.randint(1000,9999))+u'.jpg','wb') as code:
code.write(res)
except:
continue
#http://www.27270.com/ent/meinvtupian/2016/156239_20.html 第二十张图片的网址
orignurl=url.split('.html')
for i in range(2,15):
picurl = '%s_%s.html' % (orignurl,i)
#print picurl
try:
request = urllib2.Request(picurl,None,header)
response = urllib2.urlopen(request).read()
girlink = pattern.search(response).group(1)
print girlink
req = urllib2.Request(girlink,None,header)
res = urllib2.urlopen(req,None,timeout=10).read()
with open(u'PICTURE'+'/'+time.strftime('%H%M%S')+str(random.randint(1000,9999))+u'.jpg','wb') as code:
code.write(res)
except:
continue
if __name__ == '__main__':
path = os.getcwd()
new_path = os.path.join(path,u'PICTURE')
if not os.path.isdir(new_path):
os.mkdir(new_path)
links = GetUrl()
#print type(links)
GetImage(*links)
页:
[1]