Python语言技术文档

微信小程序技术文档

php语言技术文档

jsp语言技术文档

asp语言技术文档

C#/.NET语言技术文档

html5/css技术文档

javascript

点击排行

您现在的位置:首页 > 技术文档 > Python网络爬虫

Python实现登录人人网并抓取新鲜事的方法

来源:中文源码网    浏览:149 次    日期:2024-04-29 18:12:07
【下载文档:  Python实现登录人人网并抓取新鲜事的方法.txt 】


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~~)
from sgmllib import SGMLParser
import sys,urllib2,urllib,cookielib
class spider(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)
def login(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()
#print self.file
def start_h3(self,attrs):
self.h3 = True
def end_h3(self):
self.h3=False
self.h3_is_ready=True
def start_a(self,attrs):
if self.h3 or self.div:
self.a=True
def end_a(self):
self.a=False
def start_div(self,attrs):
if self.h3_is_ready == False:
return
if self.div==True:
self.depth += 1
for k,v in attrs:
if k == 'class' and v == 'content':
self.div=True;
self.h3_and_div=True #h3 and div is connected
def end_div(self):
if self.depth == 0:
self.div=False
self.h3_and_div=False
self.h3_is_ready=False
self.names=""
if self.div == True:
self.depth-=1
def handle_data(self,text):
#record the name
if self.h3 and self.a:
self.names+=text
#record says
if self.h3 and (self.a==False):
if not text:pass
else: self.dic.setdefault(self.names,[]).append(text)
return
if self.h3_and_div:
self.dic.setdefault(self.names,[]).append(text)
def show(self):
type = sys.getfilesystemencoding()
for key in self.dic:
print ( (''.join(key)).replace(' ','')).decode('utf-8').encode(type), \
( (''.join(self.dic[key])).replace(' ','')).decode('utf-8').encode(type)
renrenspider=spider('your email','your password')
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。

相关内容