import requests
import re
for yema inrange(1,75):print("正在爬取第%d页"%yema)
wangzhi ="http://www.2345.com/inner/jzw/%d.htm"%yema
response = requests.get(wangzhi)# print(response.text)# .可以替代任意一个字符# * 指前面这个字符可以出现多次
r =re.findall('<li><span class="table_left">(.*)</span>',response.text)
f =open('text','a')for i in r:try:
i = i.split('</span><span class="table_right"><a href="javascript:;" class="answer" οnclick="MM_popupMsg(')# print(i[0])
f.write(i[0])
f.write('\n')# print(i[1])except:continue# 继续 跳出当前循环,进行下一次循环
f.close()
# 匹配术:正则表达式# re
s ="""
nbvenkghmd ,fv,kgm x,dtr5foguhijhugyfgvhbjnkljhkgjhvbjjbcgfxvhbjkhvgchvbjknhvgcvhbjkhvghbjnkbhvg njbhvgbjSDTRFGJBHKNLKJHGVBJNKML;NBHVGCVHBJNKLJXFCGVHBJNKL;VFCGVHJKLHUGYFTCGVHBJHKGHCHBJKNJHVGB000000000152154@#$%^&*u(p)(trcgvhbfdxfcgASDADSASDDDD45/AD4./ADA4,4TS5RS.RASF2CZ46R87Z4knhv njkbhvjnkbhvbjn
"""# f,g R F B @import re
# # r = re.findall('f[a-z]g',s) # findall 发现所有# # r = re.findall('r[0-9]f',s) # findall 发现所有# #r = re.findall('B([0-9]*)@',s) # findall 发现所有# r =re.findall("fdxfcg(.*)k",s)# print(r)# a = '大吉大利?几万吃鸡'# a = a.split('?')# print(a[0])for i inrange(10):if i ==5:continueprint(i)