前言：通过运用正则表达式，可以简单的写一写爬虫！马上来试一试1
1,爬去图片并保存下载。
一段关于爬去美女图片的代码！（所以选择要爬的网址十分重要!看个人爱好了）
from urllib.request import urlopen,Request
import re
from urllib import request
url = 'http://www.27270.com/ent/meinvtupian/'
res = Request(url,headers={
'User-Agent':' Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
'Referer':'http://www.27270.com/ent/meinvtupian/'
})
req = urlopen(res)
result = req.read().decode('gbk')
# print(result)
pat = re.compile(r'<img src="(.*?jpg)"',re.S)
ree = re.findall(pat,result)
# print(ree)
#下载！保存路径
y= 0 #命名
for x in ree:
request.urlretrieve(x,'C:\\Users\\Administrator\\Desktop\\img1\\%s.jpg' % y)
y += 1
2，爬去文字（这里我选择已故的内涵段子！因为没啥东西，所以适合新手练练手）
from urllib.request import Request,urlopen
import re
url = 'http://www.neihanshequ.com'
res = Request(url,headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
'Referer':'http://www.neihanshequ.com'
})
req = urlopen(res)
result = req.read().decode('utf-8')
# print(result)
pat = re.compile(r'<title>(.*?)</title>.*?<div class="notice-container">(.*?)</div>',re.S)
ree = re.findall(pat,result)
print(ree)3，爬去糗事百科段子，评论数，评论人，评论
import requests
import re
url = 'http://www.qiushibaike.com'
r= requests.get(url,headers= {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
})
# print(r.text)
#段子
pat = re.compile(r'<div class="content">\n<span>\n\n\n(.*?)</span>',re.S)
ree = re.findall(pat,r.text)
# print(ree)
# 评论人数
pat1 = re.compile(r'<i class="number">(.*?)</i> 评论')
ree1 = re.findall(pat1,r.text)
# print(ree1)
pat9 = re.compile(r'<span class="dash"> · </span>\n<a href="(.*?)"',re.S)
ree9 = re.findall(pat9,r.text)
# print(ree9)
for x in range(0, len(ree)):
print('段子："{}"'.format(ree[x]))
print('评论数为:"{}"'.format(ree1[x]))
url1 = 'https://www.qiushibaike.com'+ree9[x]
r1 = requests.get(url1,headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
})
#评论
pat2 = re.compile(r'<span class="body">(.*?)</span>',re.S)
ree2 = re.findall(pat2,r1.text)
# print(ree2)
#作者
pat3 = re.compile(r'class="userlogin" target="_blank" title="(.*?)">',re.S)
ree3 = re.findall(pat3,r1.text)
# print(ree3)
#年龄
pat4 = re.compile(r'<div class="articleCommentGender manIcon">(.*?)</div>',re.S)
ree4 = re.findall(pat4,r1.text)
# print(ree4)
for y in range(0, len(ree4)):
print('糗友:"{}"'.format(ree3[y]))
print('年龄:"{}"'.format(ree4[y]))
print('评论："{}"'.format(ree2[y]))
print('-------------------------------')
print('******************************************************************************')这里用了循环！因为评论页面和主页面不在一起，所以要进行从主页面到评论页面的操作！
爬虫还没完成！同志仍需努力！！！！！！！