python抓取豆瓣图片并自动保存示例学习
环境python 2.7.6,bs4,在powershell或命令行均可运行。请确保安装了bs模块
# -*- coding:utf8 -*-
# 2013.12.36 19:41 wnlo-c209
# 抓取dbmei.com的图片。
from bs4 import beautifulsoup
import os, sys, urllib2
# 创建文件夹,昨天刚学会
path = os.getcwd() # 获取此脚本所在目录
new_path = os.path.join(path,u'豆瓣妹子')
if not os.path.isdir(new_path):
os.mkdir(new_path)
def page_loop(page=0):
url = 'http://www.dbmeizi.com/?p=%s' % page
content = urllib2.urlopen(url)
soup = beautifulsoup(content)
my_girl = soup.find_all('img')
# 加入结束检测,写的不好....
if my_girl ==[]:
print u'已经全部抓取完毕'
sys.exit(0)
print u'开始抓取'
for girl in my_girl:
link = girl.get('src')
flink = 'http://www.dbmeizi.com/' + link
print flink
content2 = urllib2.urlopen(flink).read()
with open(u'豆瓣妹子'+'/'+flink[-11:],'wb') as code: #在osc上现学的
code.write(content2)
page = int(page) + 1
print u'开始抓取下一页'
print 'the %s page' % page
page_loop(page)
page_loop().