盗光者 发表于 2021-7-25 17:10:49

python爬虫

import urllib
import urllib.request
import time
import re

for p in range(1,8):
    url='https://www.tupianzj.com/meinv/20200324/207357_'+str(p)+'.html'
    headers={'UA':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
    data=requests.get(url,headers=headers)
    data.encoding='utf-8'
    html=etree.HTML(data.text)
    license=html.xpath("//ul[@class='list_con_box_ul']/li/a/@href")
    print(license)
    print('第'+str(p)+'页所有图片网址获取完毕!')
    print('____________________________________')
    print('正在下载'+str(p)+'页所有图片,')
    time.sleep(8)
    for i in range(0,len(license)):
      print('正在爬取'+str(p)+'页的第'+str(i+1)+'位')
      url_pic="https://www.tupianzj.com"+str(license)
      headers={'UA':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
      data=requests.get(url_pic,headers=headers)
      data.encoding='utf-8'
      html=etree.HTML(data.text)
      page=html.xpath("//div[@class='pages']/ul/li/a/text()")               
      page=re.findall("\照片",page)
      url_pics=url_pic.split('.',-1)
      url_pics=url_pics+'.'+url_pics+'.'+url_pics
      for j in range(1,int(page)):
            url_page=url_pics+'_'+str(j+1)+'.html'
            headers={'UA':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
            data=requests.get(url_page,headers=headers)
            data.encoding='utf-8'
            html=etree.HTML(data.text)
            pages=html.xpath("//div[@id='bigpic']/a/img/@src")
            print(pages)
            time.sleep(1)
            urllib.request.urlretrieve(pages,'D:/新建文件夹/'+str(p)+'.'+str(i+1)+'.'+str(j)+'.jpg')
      print('下载结束了')


(新手一枚)请大家看下 ,最后我保存到哪里去了? 我文件夹里也没有

逃兵 发表于 2021-7-25 17:14:18

爬虫的基础是url不能失效
你爬的页面都404了,肯定什么都爬不出来

wp231957 发表于 2021-7-25 20:38:12

url="https://www.tupianzj.com/meinv/20210609/228790"
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
import requests
from lxml import etree
pic=[]
for x in range(1,9):
    if x==1:
      _url=".html"
    else:
      _url="_"+str(x)+".html"
    res=requests.get(url+_url,headers=headers)
    obj=etree.HTML(res.text)
    pic.append(obj.xpath("//img[@id='bigpicimg']/@src"))
for x in pic :print(x)   
页: [1]
查看完整版本: python爬虫