转Python 代码批量抓取免费高清图片！

Posted 2022-05-09 zhzhang

 

import requests
from bs4 import BeautifulSoup
import random
import time
from fake_useragent import UserAgent


for page in range(1, 11):
    fst_url = r‘https://colorhub.me/search?tag=data&page=‘.format(page)
    UA = UserAgent()
    fst_response = requests.get(fst_url, headers=‘User-Agent‘: UA.random)
    fst_soup = BeautifulSoup(fst_response.text, ‘lxml‘)
    # print(fst_soup.findAll(name=‘div‘))
    # exit()
    sec_urls = [i.find(‘a‘)[‘href‘] for i in fst_soup.findAll(name=‘div‘, attrs=‘class‘: ‘card‘)]
    pic_names = [i.find(‘a‘)[‘title‘] for i in fst_soup.findAll(name = ‘div‘, attrs=‘class‘:‘card‘)]
    for sec_url, pic_name in zip(sec_urls, pic_names):
        UA = UserAgent()
        ua = UA.random
        sec_response = requests.get(sec_url, headers=‘User-Agent‘: ua)
        sec_soup = BeautifulSoup(sec_response.text, ‘lxml‘)
        pic_url = ‘https:‘+sec_soup.find(‘img‘, ‘class‘: ‘card-img-top‘)[‘src‘]
        pic_response = requests.get(pic_url, headers=‘User-Agent‘: ua)
        with open(pic_name+‘.jpg‘, mode=‘wb‘) as fn:
            fn.write(pic_response.content)
            print(pic_name)
            seconds = random.uniform(1,3)
            time.sleep(seconds)
            fn.close()

 

请各位大虾赐教！