環境Python 2.7.6,BS4,在powershell或命令行均可運行。請確保安裝了BS模塊
代碼如下:
# -*- coding:utf8 -*-
# 2013.12.36 19:41 wnlo-c209
# 抓取dbmei.com的圖片。
from bs4 import BeautifulSoup
import os, sys, urllib2
# 創建文件夾,昨天剛學會
path = os.getcwd() # 獲取此腳本所在目錄
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')
# 加入結束檢測,寫的不好....
if my_girl ==[]:
print u'已經全部抓取完畢'
sys.exit(0)
print u'開始抓取'
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上現學的
code.write(content2)
page = int(page) + 1
print u'開始抓取下一頁'
print 'the %s page' % page
page_loop(page)
page_loop().
新聞熱點
疑難解答