Python 爬取妹子图(技术是无罪的)

  • Z时代
  • 2024-01-10
  • 分类：综合

python

...

import requests
from bs4 import BeautifulSoup
import os
import sys
class mzitu():
    def html(self, href):
        html = self.request(href)
        a = BeautifulSoup(html.text, 'lxml').find('h2', class_='main-title')
        title = a.get_text()
        print(u'开始保存：', title)
        path = str(title)
        self.mkdir(path)
        max_span = BeautifulSoup(html.text, 'lxml').find('div', class_='pagenavi').find_all('span')[-2].get_text()
        for page in range(1, int(max_span) + 1):
            page_url = href + '/' + str(page)
            self.img(page_url)
    def img(self, page_url):
        img_html = self.request(page_url)
        img_url = BeautifulSoup(img_html.text, 'lxml').find('div', class_='main-image').find('img')['src']
        self.save(img_url)
    def save(self, img_url):
        name = img_url[-6:-4]
        img = self.request(img_url)
        with open(name + '.jpg','ab') as f:
            f.write(img.content)
    def request(self, url): 
        headers = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
        content = requests.get(url, headers=headers)
        return content
    def mkdir(self, path): ##这个函数创建文件夹
        path = path.strip()
        isExists = os.path.exists(os.path.join("D:\mzitu", path))
        if not isExists:
            print(u'创建', path, u'文件夹')
            os.makedirs(os.path.join("E:\MZITU", path))
            os.chdir(os.path.join("E:\mzitu", path)) ##切换到目录
            return True
        else:
            print(u'名字叫做', path, u'的文件夹已经存在了')
            return False
Mzitu = mzitu()
Mzitu.html('http://www.mzitu.com/92251')

...

以上是 Python 爬取妹子图(技术是无罪的) 的全部内容， 来源链接： utcz.com/z/387585.html

回到顶部