from bs4 import BeautifulSoup
import urllib2
import urllib
import cookielib
urllib2.urlopen('http://www.baidu.com').read()
baseurl='https://selfsolve.apple.com/repairstatus/GetRepairDetails.do'
headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Host':'selfsolve.apple.com',
'Origin':'https://selfsolve.apple.com',
'Referer':'https://selfsolve.apple.com/repairstatus/main.do',
'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.4',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Content-Length':45,
'Content-Type':'application/x-www-form-urlencoded',
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.116 Safari/537.36',
}
postData={
'repair_id':'aaaaaa',#维修序号
'serial_number':'bbbbb'#手机序列号
}
if __name__=='__main__':
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(
cookie_support,
urllib2.HTTPHandler(debuglevel=1),
urllib2.HTTPSHandler(debuglevel=1)
)
urllib2.install_opener(opener)
StrpostData=urllib.urlencode(postData)
req=urllib2.Request(baseurl,StrpostData,headers)
rsp=urllib2.urlopen(req)
text=rsp.read()
file=open('repair.html','w')
file.write(text)
file.close()
print text
raw_input()
好了,程序就是这样子,上面说的添加cookie支持和开启调试模式就是下面这段代码
代码如下:
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(
cookie_support,
urllib2.HTTPHandler(debuglevel=1),
urllib2.HTTPSHandler(debuglevel=1)
)
urllib2.install_opener(opener)
然后可以很方便的看到程序运行时候的输出,如下图
接下来就可以通过得到的html来抓取需要的信息了.