爬虫------爬取搜狗图片

一、单线程

# author:WN
# datetime:2019/10/30 9:07
import requests
import re


def image_urls():
    search_name = input("请输入你要搜索的图片:")
    search_num = int(input("一页有48张图片，需要几页："))
    # url存放的总列表
    all_urls = list()
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
    }
    # query参数的值是要搜多的图片名，start参数的值是图片开始的下标
    for i in range(0, search_num*48, 48):
        url = 'https://pic.sogou.com/pics?query={0}&mode=1&start={1}&reqType=ajax&reqFrom=result&tn=0'.format(search_name, i)
        response = requests.get(url, headers=headers)
        url_list = re.findall('"thumbUrl":"(.*?)"', response.text)
        # 输入的关键字没有寻找到图片时
        if len(url_list) == 0:
            print("没有图片!")
        all_urls.extend(url_list)
    download(all_urls, headers)


def download(url_list, headers):
    count = 0
    for url in url_list:
        response = requests.get(url, headers=headers)
        with open('E:/搜狗图片/%s.jpg' % count, 'ab') as f:
            f.write(response.content)
        count += 1


if __name__ == '__main__':
    image_urls()

 

二、多线程

# author:WN
# datetime:2019/10/30 9:07
import requests
import re
import threading

threads = list()


def image_urls():
    search_name = input("请输入你要搜索的图片:")
    search_num = int(input("一页有48张图片，需要几页："))
    # 保存的图片名
    count = 0
    # url存放的总列表
    all_urls = list()
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
    }
    # query参数的值是要搜多的图片名，start参数的值是图片开始的下标
    for i in range(0, search_num*48, 48):
        url = 'https://pic.sogou.com/pics?query={0}&mode=1&start={1}&reqType=ajax&reqFrom=result&tn=0'.format(search_name, i)
        response = requests.get(url, headers=headers)
        url_list = re.findall('"thumbUrl":"(.*?)"', response.text)
        # 输入的关键字没有寻找到图片时
        if len(url_list) == 0:
            print("没有图片!")
        all_urls.extend(url_list)
    for img_url in all_urls:
        t = threading.Thread(target=download, args=(img_url, headers, count))
        # 设置为后台线程，不会随主线程的结束而结束
        t.setDaemon(False)
        t.start()
        count += 1
        threads.append(t)


def download(url, headers, count):
    response = requests.get(url, headers=headers)
    with open('E:/搜狗图片/%s.jpg' % count, 'ab') as f:
        f.write(response.content)


if __name__ == '__main__':
    image_urls()
    # 阻塞主线程
    for j in threads:
        j.join()