这方面没有吧，我是根据网上的博客自己写的一个小的代码。。。。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# -*- coding:utf-8 -*-#
#-python 2.7-#
import shutil
import urllib
import urllib2
import re,os,glob,string,sys
#=====================================================#
# MAIN #
#=====================================================#
def main():
#---also canset before the main() function---#
reload(sys)
sys.setdefaultencoding("utf-8" )
#---------------------------------------------#
global j #--global j is the name of the '.txt' file--#
j=1
url_home='
http://www.qiushibaike.com'
url_lists=['/8hr/page/','/hot/page/','/history/page/']
path=os.getcwd()
ifos.path.exists(path+'\DUANZI'):
shutil.rmtree(path+'\DUANZI')
os.mkdir('DUANZI')
for url_listin url_lists:
ALL_CON(url_list,url_home)
#=====================================================#
# GET URL #
#=====================================================#
def ALL_CON(url1,url2):
i=1
lists=[]
while i:
# printi #----use for debug---#
url_real=url2+url1+str(i)
list1=GetPage(url_real)
DuanZi(list1)
if list1not in lists:
lists.append(list1)
i+=1
continue
else:
break
#======================================================#
# GET HTML CODE #
#======================================================#
def GetPage(url):
headers ={'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, likeGecko) Chrome/50.0.2652.2 Safari/537.36'}
req =urllib2.Request(url,headers = headers)
myResponse = urllib2.urlopen(req)
myResponse=myResponse.read()
myResponse=myResponse.decode('utf-8')
myResponse=re.sub('','',myResponse)
myResponse=re.sub('\t','',myResponse)
myResponse=re.sub('\n','',myResponse)
#---can usere.compile() instand of re.sub()---#
findall_duanzi=re.findall('<divclass="articleblockuntaggedmb15".*?<divclass="single-clear">',myResponse)
#---find allclass='article block untagged mb15' in HTML code &&return a list----#
i=0
whilei<len(findall_duanzi):
iffindall_duanzi[i].find('<imgsrc=') == -1:
i+=1
continue
else:
delfindall_duanzi[i]#-----delete imagine substance----#
i+=1
findall_list=''.join(findall_duanzi)
returnfindall_list
#===================================================#
# WRITE IN TXT FILE #
#===================================================#
def DuanZi(list1):
path=os.getcwd()
os.chdir(path+'\DUANZI')
duanzis=[]
duanzi=re.compile('<divclass="content">.*?</div>')
duanzis=duanzi.findall(list1)
txt_last=[]
global j
i=1
for x induanzis:
txt_name=str(j)+'.txt'
fp=open(txt_name,'w')
list2=[]
list2=(re.sub('<.*?>','',x)).split('"')#-----gain all the chianese below---#
txt_last=''.join(list2)
fp.write(txt_last)
fp.close()
i+=1
j+=1
os.chdir(path)
#============RUN===========================#
if __name__ == '__main__':
main()
上面这些代码，你只要改一下User-Agent的值就应该可以运行了本回答被提问者采纳