[PRG][开源作品] 百度图片下载器

发表在 P.R.G! 08-24 16:42:37

0 2015 0

#匡名ip来自网络，侵权删。
#python3环境

from bs4 import BeautifulSoup
import requests
import random

def get_ip_list(url, headers):
    web_data = requests.get(url, headers=headers)
    soup = BeautifulSoup(web_data.text, 'lxml')
    ips = soup.find_all('tr')
    ip_list = []
    for i in range(1, len(ips)):
        ip_info = ips[i]
        tds = ip_info.find_all('td')
        ip_list.append(tds[1].text + ':' + tds[2].text)
    return ip_list

def get_random_ip(ip_list):
    proxy_list = []
    for ip in ip_list:
        proxy_list.append('http://' + ip)
    proxy_ip = random.choice(proxy_list)
    proxies = {'http': proxy_ip}
    return proxies

if __name__ == '__main__':
    url = 'http://www.xicidaili.com/nn/' #请求匡名ip
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
    } #请求头部分
    ip_list = get_ip_list(url, headers=headers) #获取到的ip表单
    proxies = get_random_ip(ip_list) #随机抽取一个

page_n = 0 #从第“1”页抓取

for un_n in range(10): #循环10次，也就是获取300张
	a = requests.get("https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=头像&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&word=头像&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&fr=&pn="+str(page_n)+"&rn=30&gsm=3c&1503210302185=").json() #获取图片链接
	for files_n in range(30): #循环30次，每次得到一张
		print('正在获取... -->',files_n,page_n) #显示状态
		ir = requests.get(a['data'][int(files_n)]['thumbURL'],proxies=proxies,headers=headers) 获取图片
		if ir.status_code == 200: #如果状态码200，下载图片
			with open('D:/photo/'+str(files_n)+' '+str(page_n)+'.jpg', 'wb') as f:
				for chunk in ir:
					f.write(chunk)
	page_n += 30 #每次增加30