Python实现登录人人网并抓取新鲜事的方法
本文实例讲述了Python实现登录人人网并抓取新鲜事的方法。分享给大家供大家参考。具体如下：
这里演示了Python登录人人网并抓取新鲜事的方法（抓取后的排版不太美观~~）
fromsgmllibimportSGMLParser
importsys,urllib2,urllib,cookielib
classspider(SGMLParser):
def__init__(self,email,password):
SGMLParser.__init__(self)
self.h3=False
self.h3_is_ready=False
self.div=False
self.h3_and_div=False
self.a=False
self.depth=0
self.names=""
self.dic={}
self.email=email
self.password=password
self.domain='renren.com'
try:
cookie=cookielib.CookieJar()
cookieProc=urllib2.HTTPCookieProcessor(cookie)
except:
raise
else:
opener=urllib2.build_opener(cookieProc)
urllib2.install_opener(opener)
deflogin(self):
url='http://www.renren.com/PLogin.do'
postdata={
'email':self.email,
'password':self.password,
'domain':self.domain
}
req=urllib2.Request(
url,
urllib.urlencode(postdata)
)
self.file=urllib2.urlopen(req).read()
#printself.file
defstart_h3(self,attrs):
self.h3=True
defend_h3(self):
self.h3=False
self.h3_is_ready=True
defstart_a(self,attrs):
ifself.h3orself.div:
self.a=True
defend_a(self):
self.a=False
defstart_div(self,attrs):
ifself.h3_is_ready==False:
return
ifself.div==True:
self.depth+=1
fork,vinattrs:
ifk=='class'andv=='content':
self.div=True;
self.h3_and_div=True#h3anddivisconnected
defend_div(self):
ifself.depth==0:
self.div=False
self.h3_and_div=False
self.h3_is_ready=False
self.names=""
ifself.div==True:
self.depth-=1
defhandle_data(self,text):
#recordthename
ifself.h3andself.a:
self.names+=text
#recordsays
ifself.h3and(self.a==False):
ifnottext:pass
else:self.dic.setdefault(self.names,[]).append(text)
return
ifself.h3_and_div:
self.dic.setdefault(self.names,[]).append(text)
defshow(self):
type=sys.getfilesystemencoding()
forkeyinself.dic:
print((''.join(key)).replace('','')).decode('utf-8').encode(type),\
((''.join(self.dic[key])).replace('','')).decode('utf-8').encode(type)
renrenspider=spider('youremail','yourpassword')
renrenspider.login()
renrenspider.feed(renrenspider.file)
renrenspider.show()
希望本文所述对大家的Python程序设计有所帮助。