新手爬虫——爬妹子

真正的西瓜籽

赞，棒，LSP

noah-py

愷龍

爬虫学的好，牢饭吃到饱

                               
登录/注册后可看大图

愷龍

文件损坏了啊

                               
登录/注册后可看大图

小白_Pythong

文件损坏,下载不了！！！

embededarm

学习中！！

embededarm

压缩包打不开。

淡淡凉

Lesl1e 发表于 2021-4-14 13:21
这lxml也安装了

1. import requests
   
2. #from lxml import etree  python3.5以上版本不可这样导入
   
3. from lxml import html
   
4. etree = html.etree
   
5. import os
   
6. import time
   
7. 
   
8. def geturl(url):
   
9.     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"}
   
10.     #params = {"show_raw":1}
    
11.     #response = requests.get(url,params=params,headers = headers)
    
12.     response = requests.get(url,headers = headers)
    
13.     response.encoding = 'gbk'
    
14.     html = response.text
    
15.     return html
    
16. 
    
17. def get_mggs(url):
    
18.     mggs = []
    
19.     html = geturl(url)
    
20.     html = etree.HTML(html)
    
21.     items = html.xpath('//ul[@class="list_con_box_ul"]/li')
    
22. 
    
23.     for li in items:
    
24.         href = li.xpath("./a/@href")[0]
    
25.         title = li.xpath("./a/@title")[0]
    
26.         mgg = [title,href]
    
27.         mggs.append(mgg)
    
28. 
    
29.     return mggs
    
30. 
    
31. def getmgg():
    
32.     mggs = get_mggs(url)
    
33.     for mgg in mggs:
    
34.         count = 1
    
35.         mggurl1 = url.split("/meinv")[0] + mgg[1]
    
36.         if not os.path.exists(mgg[0]):
    
37.             dil = dils(mgg[0])
    
38. 
    
39.         else:
    
40.             os.chdir(mgg[0])
    
41. 
    
42.         for i in range(15):
    
43.             mggurl = mggurl1
    
44.             if count == 1:
    
45.                 mggurl = mggurl1
    
46. 
    
47.             else:
    
48.                 mggurl = mggurl1.split(".html")[0] + "_" + str(count) + ".html"
    
49. 
    
50.             count += 1
    
51. 
    
52.             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"}
    
53.             resp = requests.get(url=mggurl,headers=headers)
    
54.             links = []
    
55.             if resp.status_code ==200:
    
56.                 html = resp.text
    
57.                 html = etree.HTML(html)
    
58.                 link = html.xpath('//div[@id="bigpic"]/a[2]/img/@src')[0]
    
59.                 mm_jpg = requests.get(link,headers=headers)
    
60. 
    
61.                 with open(link.split("/")[-1],'wb')as f:
    
62.                     f.write(mm_jpg.content)
    
63.                     print("成功下载一张图片")
    
64.                     time.sleep(1)
    
65.         os.chdir(".\\..")
    
66. 
    
67.         #print("成功下载一套图片")
    
68. 
    
69. 
    
70. def dils(name = "ooxx"):
    
71.     os.mkdir(name)
    
72.     os.chdir(name)
    
73. 
    
74. 
    
75. if __name__ == "__main__":
    
76.    
    
77.     url1 = "https://www.tupianzj.com/meinv/"
    
78.     lis = {"清纯美女":"xiezhen/","性感":"xinggan/",
    
79.            "古装":"guzhuang/","人体艺术":"yishu/",
    
80.            "香车美女":"chemo/","丝袜美女":"siwa/"
    
81.         }
    
82.     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）")
    
83.     url = url1 + lis[name]
    
84. 
    
85.     geturl(url)
    
86.     mggs_url = get_mggs(url)
    
87.     maggs = getmgg()
    

复制代码

淡淡凉

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~

我刚开始学Python你就给我看这个？

1589895304

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

文件损坏 无法解压