爬取千库网ppt_python爬取千库网

但是点进去就没了

这里先来测试是否有反爬虫

import requests

from bs4 import BeautifulSoup

import os

html = requests.get('https://i588ku.com/beijing/0-0-default-0-8-0-0-0-0-1/')

print(html.text)

输出是404，添加个ua头就可以了

可以看到每个图片都在一个div class里面，比如fl marony-item bglist_5993476，是3个class但是最后一个编号不同就不取

我们就可以获取里面的url

import requests

from bs4 import BeautifulSoup

import os

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'

}

html = requests.get('https://i588ku.com/beijing/0-0-default-0-8-0-0-0-0-1/',headers=headers)

soup = BeautifulSoup(html.text,'lxml')

Urlimags = soup.select('div.fl.marony-item div a')

for Urlimag in Urlimags:

print(Urlimag['href'])

输出结果为

//i588ku.com/ycbeijing/5993476.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5991004.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5990729.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5991308.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5990409.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5989982.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5978978.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5993625.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5990728.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5951314.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5992353.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5993626.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5992302.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5820069.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5804406.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5960482.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5881533.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5986104.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5956726.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5986063.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5978787.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5954475.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5959200.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5973667.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5850381.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5898111.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5924657.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5975496.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5928655.html

//i588ku.com/comnew/vip/

//i588ku.com/ycbeijing/5963925.html

//i588ku.com/comnew/vip/

这个/vip是广告，过滤一下

for Urlimag in Urlimags:

if 'vip' in Urlimag['href']:

continue

print('http:'+Urlimag['href'])

然后用os写入本地

import requests

from bs4 import BeautifulSoup

import os

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'

}

html = requests.get('https://i588ku.com/beijing/0-0-default-0-8-0-0-0-0-1/',headers=headers)

soup = BeautifulSoup(html.text,'lxml')

Urlimags = soup.select('div.fl.marony-item div a')

for Urlimag in Urlimags:

if 'vip' in Urlimag['href']:

continue

# print('http:'+Urlimag['href'])

imgurl = requests.get('http:'+Urlimag['href'],headers=headers)

imgsoup = BeautifulSoup(imgurl.text,'lxml')

imgdatas = imgsoup.select_one('.img-box img')

title = imgdatas['alt']

print('无水印:','https:'+imgdatas['src'])

if not os.path.exists('千图网图片'):

os.mkdir('千图网图片')

with open('千图网图片/{}.jpg'.format(title),'wb')as f:

f.write(requests.get('https:'+imgdatas['src'],headers=headers).content)

import requests

from bs4 import BeautifulSoup

import os

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'

}

for i in range(1,11):

print('正在下载第{}页'.format(i))

html = requests.get('https://i588ku.com/beijing/0-0-default-0-8-0-0-0-0-{}/'.format(i),headers=headers)

soup = BeautifulSoup(html.text,'lxml')

Urlimags = soup.select('div.fl.marony-item div a')

for Urlimag in Urlimags:

if 'vip' in Urlimag['href']:

continue

# print('http:'+Urlimag['href'])

imgurl = requests.get('http:'+Urlimag['href'],headers=headers)

imgsoup = BeautifulSoup(imgurl.text,'lxml')

imgdatas = imgsoup.select_one('.img-box img')

title = imgdatas['alt']

print('无水印:','https:'+imgdatas['src'])

if not os.path.exists('千图网图片'):

os.mkdir('千图网图片')

with open('千图网图片/{}.jpg'.format(title),'wb')as f:

f.write(requests.get('https:'+imgdatas['src'],headers=headers).content)