python 采集美图录网站的图片

【实例截图】

【核心代码】

import requests
from bs4 import BeautifulSoup
import os
import chardet
from chardet import detect
import re
 
 
 
 
 
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",
    'Accept': "text/html,application/xhtml xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    'Accept-Encoding': 'gzip',
    "Referer": "https://www.meitulu.com/"
}   #头部文件
path="jpg"
os.chdir(path)
 
url = 'https://www.meitulu.com/t/qingdouke/'  #青豆客
 
 
#'https://www.meitulu.com/t/youwuguan/'  尤物馆
#'https://www.meitulu.com/t/girlt/'  果团网 , 'https://www.meitulu.com/t/mistar/', 魅妍社
#'https://www.meitulu.com/t/1088/', 星颜社 'https://www.meitulu.com/t/ishow/', iSHOW爱秀
#'https://www.meitulu.com/t/huayan/',花の颜 'https://www.meitulu.com/t/xingleyuan/',星乐园
#'https://www.meitulu.com/t/tukmo/', 'https://www.meitulu.com/t/aiss/',
#'https://www.meitulu.com/t/miitao/', 'https://www.meitulu.com/t/uxing/',
#'https://www.meitulu.com/t/taste/',  'https://www.meitulu.com/t/micat/',
#'https://www.meitulu.com/t/candy/', 'https://www.meitulu.com/t/yunvlang/',
#'https://www.meitulu.com/t/youmihui/', 'https://www.meitulu.com/t/1113/',
#'https://www.meitulu.com/t/1209/', 'https://www.meitulu.com/t/imiss/',
#'https://www.meitulu.com/t/yingsihui-wings/', https://www.meitulu.com/t/dianannan/ 嗲囡囡
 
response1 = requests.get(url, headers=headers, allow_redirects=False)  
 
e = chardet.detect(response1.content)['encoding']
response1.encoding = e
 
html_soup1 = BeautifulSoup(response1.text, 'lxml')
all_a = html_soup1.find('ul', class_='img').find_all('li') #
count=0
for l in all_a:
    count = count   1
    a = l.a
    #print(a)
 
 
    if (a.find('img') == None):
        continue
    else:
 
        href = a["href"]
        print(href)
 
        href2=href.replace('.html', '_')
        response2 = requests.get(href, headers=headers)
 
        e = chardet.detect(response2.content)['encoding']
        response2.encoding = e
 
        html_soup2 = BeautifulSoup(response2.text, 'lxml')
        name = html_soup2.find('title').text.replace('/', '-')
        os.mkdir(name)
        print(name)
        img1 = html_soup2.find("div", {"class": "content"}).find_all("img")
        page = html_soup2.find("div", {"id": "pages"}).find_all('a')[-2]
        max_page = page.get_text()
 
 
        for pic in img1:
            os.chdir(name)
            count = count   1
            pic1 = pic['src']
            # print(pic1)
            pic2 = requests.get(pic1, headers=headers)
            f = open(name str(count)   '.jpg', 'ab')  ##写入多媒体文件必须要 b 这个参数！！必须要！！
            f.write(pic2.content)  ##多媒体文件要是用conctent哦！
            f.close()
            os.chdir("C:\\Users\\Administrator\\Desktop\\jpg")
 
        for i in range(2, int(max_page)   1):
            os.chdir(name)
            href3 = href2   str(i)   '.html'
            response3 = requests.get(href3, headers=headers)
 
            html_soup3 = BeautifulSoup(response3.text, 'lxml')
            img1 = html_soup3.find("div", {"class": "content"}).find_all("img")
            # print(href3)
            for pic in img1:
                count = count   1
 
                pic1 = pic['src']
                # print(pic1)
                pic2 = requests.get(pic1, headers=headers)
                f = open(name str(count)   '.jpg', 'ab')  
                f.write(pic2.content)  
                f.close()
            os.chdir("C:\\Users\\Administrator\\Desktop\\jpg")
 
 
print("完成！")