新手爬虫——爬妹子

愷龍 · 发表于 2021-4-15 17:02:48

爬虫学的好，牢饭吃到饱

登录/注册后可看大图

愷龍 · 发表于 2021-4-15 17:04:05

文件损坏了啊

登录/注册后可看大图

小白_Pythong · 发表于 2021-4-16 17:06:44

文件损坏,下载不了！！！

embededarm · 发表于 2021-4-17 12:31:11

学习中！！

embededarm · 发表于 2021-4-17 13:47:53

压缩包打不开。

淡淡凉 · 发表于 2021-4-17 15:47:47

Lesl1e 发表于 2021-4-14 13:21
这lxml也安装了

import requests
#from lxml import etree  python3.5以上版本不可这样导入
from lxml import html
etree = html.etree
import os
import time

def geturl(url):
    headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36"}
    #params = {"show_raw":1}
    #response = requests.get(url,params=params,headers = headers)
    response = requests.get(url,headers = headers)
    response.encoding = 'gbk'
    html = response.text
    return html

def get_mggs(url):
    mggs = []
    html = geturl(url)
    html = etree.HTML(html)
    items = html.xpath('//ul[@class="list_con_box_ul"]/li')

    for li in items:
        href = li.xpath("./a/@href")[0]
        title = li.xpath("./a/@title")[0]
        mgg = [title,href]
        mggs.append(mgg)

    return mggs

def getmgg():
    mggs = get_mggs(url)
    for mgg in mggs:
        count = 1
        mggurl1 = url.split("/meinv")[0] + mgg[1]
        if not os.path.exists(mgg[0]):
            dil = dils(mgg[0])

        else:
            os.chdir(mgg[0])

        for i in range(15):
            mggurl = mggurl1
            if count == 1:
                mggurl = mggurl1

            else:
                mggurl = mggurl1.split(".html")[0] + "_" + str(count) + ".html"

            count += 1

            headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36"}
            resp = requests.get(url=mggurl,headers=headers)
            links = []
            if resp.status_code ==200:
                html = resp.text
                html = etree.HTML(html)
                link = html.xpath('//div[@id="bigpic"]/a[2]/img/@src')[0]
                mm_jpg = requests.get(link,headers=headers)

                with open(link.split("/")[-1],'wb')as f:
                    f.write(mm_jpg.content)
                    print("成功下载一张图片")
                    time.sleep(1)
        os.chdir(".\\..")

        #print("成功下载一套图片")


def dils(name = "ooxx"):
    os.mkdir(name)
    os.chdir(name)


if __name__ == "__main__":
    
    url1 = "https://www.tupianzj.com/meinv/"
    lis = {"清纯美女":"xiezhen/","性感":"xinggan/",
           "古装":"guzhuang/","人体艺术":"yishu/",
           "香车美女":"chemo/","丝袜美女":"siwa/"
        }
    name = input("选择要下载的图片分类（清纯美女,性感,古装,人体艺术,香车美女,丝袜美女）")
    url = url1 + lis[name]

    geturl(url)
    mggs_url = get_mggs(url)
    maggs = getmgg()

淡淡凉 · 发表于 2021-4-17 15:48:38

import requests
#from lxml import etree  python3.5以上版本不可这样导入
from lxml import html
etree = html.etree
import os
import time

def geturl(url):
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36"}
#params = {"show_raw":1}
#response = requests.get(url,params=params,headers = headers)
response = requests.get(url,headers = headers)
response.encoding = 'gbk'
html = response.text
return html

def get_mggs(url):
mggs = []
html = geturl(url)
html = etree.HTML(html)
items = html.xpath('//ul[@class="list_con_box_ul"]/li')

for li in items:
      href = li.xpath("./a/@href")[0]
      title = li.xpath("./a/@title")[0]
      mgg = [title,href]
      mggs.append(mgg)

return mggs

def getmgg():
mggs = get_mggs(url)
for mgg in mggs:
      count = 1
      mggurl1 = url.split("/meinv")[0] + mgg[1]
      if not os.path.exists(mgg[0]):
         dil = dils(mgg[0])

      else:
         os.chdir(mgg[0])

      for i in range(15):
         mggurl = mggurl1
         if count == 1:
            mggurl = mggurl1

         else:
            mggurl = mggurl1.split(".html")[0] + "_" + str(count) + ".html"

         count += 1

         headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36"}
         resp = requests.get(url=mggurl,headers=headers)
         links = []
         if resp.status_code ==200:
            html = resp.text
            html = etree.HTML(html)
            link = html.xpath('//div[@id="bigpic"]/a[2]/img/@src')[0]
            mm_jpg = requests.get(link,headers=headers)

            with open(link.split("/")[-1],'wb')as f:
                  f.write(mm_jpg.content)
                  print("成功下载一张图片")
                  time.sleep(1)
      os.chdir(".\\..")

      #print("成功下载一套图片")

def dils(name = "ooxx"):
os.mkdir(name)
os.chdir(name)

if __name__ == "__main__":

url1 = "https://www.tupianzj.com/meinv/"
lis = {"清纯美女":"xiezhen/","性感":"xinggan/",
         "古装":"guzhuang/","人体艺术":"yishu/",
         "香车美女":"chemo/","丝袜美女":"siwa/"
      }
name = input("选择要下载的图片分类（清纯美女,性感,古装,人体艺术,香车美女,丝袜美女）")
url = url1 + lis[name]

geturl(url)
mggs_url = get_mggs(url)
maggs = getmgg()
[code][/code]

花哗哗~ · 发表于 2021-4-20 11:39:33

我刚开始学Python你就给我看这个？

1589895304 · 发表于 2021-4-24 10:49:28

FengYang.X 发表于 2021-4-14 17:22
文件损坏了啊

直接改后缀名就行了

Puppet16 · 发表于 2021-5-29 14:13:12

文件损坏无法解压

账号		自动登录	找回密码
密码			立即注册

[技术交流] 新手爬虫——爬妹子