python爬取图片源码_python抓取百度图片源码

#!/usr/bin/python

# -*- coding:utf-8 -*-

import httplib2

import urllib.request

import json

#import urllib2

import re

import os

import string

class BaiduImage(object):

def __init__(self):

super(BaiduImage, self).__init__()

print

u'图片获取中,CTRL+C 退出程序...'

self.page = 60 # 当前页数

if not os.path.exists(r'./image'):

os.mkdir(r'./image')

def request(self):

try:

urlError=""

while 1:

conn = httplib2.Http()

request_url = 'http://image.baidu.com/search/avatarjson?tn=resultjsonavatarnew&ie=utf-8&word=风景&cg=girl&rn=60&pn=' + str(

self.page)

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.0',

'Content-type': 'test/html'}

# body = urllib.urlencode({'tn':'resultjsonavatarnew','ie':'utf-8','word':'%E7%BE%8E%E5%A5%B3','cg':'girl','pn':self.page,'rn':'60'})

# conn.request( request_url,'GET', body=None, headers=headers)

resp,content = conn.request(request_url,'GET', body=None, headers=headers)

# print r.status

if resp.status == 200:

data =content

#data =unicode(data, errors='ignore')

d= data.decode("UTF-8")

decode = json.loads(d)

urlError=decode

self.download(decode['imgs'])

self.page += 60

print(self.page)

except Exception as e:

print (e+urlError)

finally:

print(conn)

def download(self, data):

imgCount=0

for d in data:

# url = d['thumbURL'] 缩略图 尺寸200

# url = d['hoverURL'] 尺寸360

try:

url = d['objURL']

print(url)

data = urllib.request.urlopen(url).read()

pattern = re.compile(r'.*/(.*?)\.jpg', re.S)

item = re.findall(pattern, url)

if item is None:

continue

if ".jpg" in url:

FileName = str('image/') + item[0] + str('.jpg')

if f.__exit__(FileName):

with open(FileName, 'wb') as f:

f.write(data)

else:

print(FileName+"存在!")

except Exception as e:

print(e)

finally:

imgCount+=1

print(imgCount.__str__() +":"+url)

if __name__ == '__main__':

bi = BaiduImage()

bi.request()