很垃圾的爬虫代码，关于妹子的，只能爬取一个网页...

zrsteen · 发表于 2020-3-18 17:54:03

马上注册，结交更多好友，享用更多功能^_^

您需要登录才可以下载或查看，没有账号？立即注册

x

import requests
import urllib.request
import re
def open_url(url):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
req = requests.get(url = url,headers=headers)
return req

url1 = 'http://www.rentifq.com/rentiyishu/34/1239'
url2 = url1 + '.html'
jpg_all = []
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
response = requests.get(url = url2,headers=headers)
response = response.text
l = re.findall('1 <A HREF="([\s\S]*)</a> <A', response)
for i in l:
ur = re.findall('HREF="([\s\S]*?)">', i)
ur =len(ur) + 2
print('共%d页'%ur)

r = re.findall('img alt=([\s\S]*?.jpg)',response)
for each in r:
jpg = re.findall('src="(/[\s\S]*?.jpg)',each)
jpg = 'http://www.rentifq.com'+jpg[0]
jpg_all.append(jpg)

for i in range(ur+1):
if i > 1:
 url = url1 + '$' + str(i) + '.html'
 response = requests.get(url=url, headers=headers)
 response = response.text
 r = re.findall('img alt=([\s\S]*?.jpg)', response)
 for each in r:
 jpg = re.findall('src="(/[\s\S]*?.jpg)', each)
 jpg = 'http://www.rentifq.com' + jpg[0]
 jpg_all.append(jpg)
print(jpg_all)

for i in jpg_all:
print(i)
filname = i.split('/'[-1][-1])
print(filname[-1])
img = open_url(i).content
with open(filname[-1],'wb') as f:
 f.write(img)

没封装好，大佬men2有没有升级的方案，或者全爬的思路......http://www.ren删tifq.com/

zrsteen · 发表于 2020-3-18 18:38:56

import requests
import re

def open_url(url):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
req = requests.get(url = url,headers=headers)
return req

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}

res = requests.get(url = 'http://www.rentifq.com/',headers = headers)
res= res.text

ur = re.findall('<a href=[\s\S]*?.html',res)
for l in ur:
ul = re.findall('<a href="([\s\S]*?).html',l) #获取页面所有的网址
# print(ul)

for each1 in ul:#一个网址一个网址的遍历打开爬
 print(each1)
 if len(each1) <=30:
 url1 = 'http://www.rentifq.com'+ each1
 print(url1)
 url2 = url1 + '.html'
 jpg_all = []
 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
 response = requests.get(url = url2,headers=headers)
 response = response.text
 l = re.findall('1 <A HREF="([\s\S]*)</a> <A', response)
 for i in l:
 ur = re.findall('HREF="([\s\S]*?)">', i)
 ur =len(ur) + 2
 print('共%d页'%ur)

 r = re.findall('img alt=([\s\S]*?.jpg)',response)
 for each in r:
 jpg = re.findall('src="(/[\s\S]*?.jpg)',each)
 jpg = 'http://www.rentifq.com'+jpg[0]
 jpg_all.append(jpg)

 for i in range(ur+1):
 if i > 1:
 url = url1 + '$' + str(i) + '.html'
 response = requests.get(url=url, headers=headers)
 response = response.text
 r = re.findall('img alt=([\s\S]*?.jpg)', response)
 for each in r:
 jpg = re.findall('src="(/[\s\S]*?.jpg)', each)
 jpg = 'http://www.rentifq.com' + jpg[0]
 jpg_all.append(jpg)
 print(jpg_all)

 for i in jpg_all:
 print(i)
 filname = i.split('/'[-1][-1])
 print(filname[-1])
 img = open_url(i).content
 with open(filname[-1],'wb') as f:
 f.write(img)

更新版..............

zrsteen · 发表于 2020-3-18 19:28:02

import requests
import re

def open_url(url):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
req = requests.get(url = url,headers=headers)
return req

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}

res = requests.get(url = 'http://www.rentifq.com/',headers = headers)
res= res.text

ur = re.findall('<a href=[\s\S]*?.html',res)
for l in ur:
ul = re.findall('<a href="([\s\S]*?).html',l) #获取页面所有的网址
# print(ul)

for each1 in ul:#一个网址一个网址的遍历打开爬
 if len(each1) <=30:
 url1 = 'http://www.rentifq.com'+ each1
 print(url1)
 url2 = url1 + '.html'
 jpg_all = []
 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}
 response = requests.get(url = url2,headers=headers)
 response = response.text
 l = re.findall('1 <A HREF="([\s\S]*)</a> <A', response)
 for i in l:
 ur = re.findall('HREF="([\s\S]*?)">', i)
 ur =len(ur) + 2
 print('共%d页'%ur)

 r = re.findall('img alt=([\s\S]*?.jpg)',response)
 for each in r:
 jpg = re.findall('src="(/[\s\S]*?.jpg)',each)
 jpg = 'http://www.rentifq.com'+jpg[0]
 jpg_all.append(jpg)

 for i in range(ur+1):
 if i > 1:
 url = url1 + '$' + str(i) + '.html'
 response = requests.get(url=url, headers=headers)
 response = response.text
 r = re.findall('img alt=([\s\S]*?.jpg)', response)
 for each in r:
 jpg = re.findall('src="(/[\s\S]*?.jpg)', each)
 jpg = 'http://www.rentifq.com' + jpg[0]
 jpg_all.append(jpg)
 print(jpg_all)

 for i in jpg_all:
 print(i)
 filname = i.split('/'[-1][-1])
 img = open_url(i).content

 with open(str(filname[-2])+filname[-1],'wb') as f:
 f.write(img)

最终版懒动了 好像整个网页都可以爬

gmd8 · 发表于 2020-3-18 21:26:11

好厉害呀，

弱爆了 · 发表于 2020-3-20 09:14:14

牛皮啊

账号		自动登录	找回密码
密码			立即注册

[技术交流] 很垃圾的爬虫代码，关于妹子的，只能爬取一个网页...

马上注册，结交更多好友，享用更多功能^_^