Python登录人人网并抓取新鲜事

from sgmllib import SGMLParser

02	import sys,urllib2,urllib,cookielib

03	class spider(SGMLParser):

04	def __init__(self,email,password):

05	SGMLParser.__init__(self)

06	self.h3=False

07	self.h3_is_ready=False

08	self.div=False

09	self.h3_and_div=False

10	self.a=False

11	self.depth=0

12	self.names=""

13	self.dic={}

14

15	self.email=email

16	self.password=password

17	self.domain='renren.com'

18

try:

19	cookie=cookielib.CookieJar()

20	cookieProc=urllib2.HTTPCookieProcessor(cookie)

21

except:

22

raise

23

else:

24	opener=urllib2.build_opener(cookieProc)

25	urllib2.install_opener(opener)

26

27	def login(self):

28	url='http://www.renren.com/PLogin.do'

29	postdata={

30	'email':self.email,

31	'password':self.password,

32	'domain':self.domain

33

}

34	req=urllib2.Request(

35

url,

36	urllib.urlencode(postdata)

37

)

38

39	self.file=urllib2.urlopen(req).read()

40	#print self.file

41	def start_h3(self,attrs):

42	self.h3 = True

43	def end_h3(self):

44	self.h3=False

45	self.h3_is_ready=True

46

47	def start_a(self,attrs):

48	if self.h3 or self.div:

49	self.a=True

50	def end_a(self):

51	self.a=False

52

53	def start_div(self,attrs):

54	if self.h3_is_ready == False:

55

return

56	if self.div==True:

57	self.depth += 1

58

59	for k,v in attrs:

60	if k == 'class' and v == 'content':

61	self.div=True;

62	self.h3_and_div=True   #h3 and div is connected

63	def end_div(self):

64	if self.depth == 0:

65	self.div=False

66	self.h3_and_div=False

67	self.h3_is_ready=False

68	self.names=""

69	if self.div == True:

70	self.depth-=1

71	def handle_data(self,text):

72	#record the name

73	if self.h3 and self.a:

74	self.names+=text

75	#record says

76	if self.h3 and (self.a==False):

77	if not text:pass

78	else: self.dic.setdefault(self.names,[]).append(text)

79

return

80	if self.h3_and_div:

81	self.dic.setdefault(self.names,[]).append(text)

82

83	def show(self):

84	type = sys.getfilesystemencoding()

85	for key in self.dic:

86	print ( (''.join(key)).replace(' ','')).decode('utf-8').encode(type), \

87	( (''.join(self.dic[key])).replace(' ','')).decode('utf-8').encode(type)

88

89

90

91

92	renrenspider=spider('your email','your password')

93	renrenspider.login()

94	renrenspider.feed(renrenspider.file)

95	renrenspider.show()