爬取百度图片

使用说明:只要输入你想要的关键字即可(input已经提示了- -)，然后在第29行那放你想要的文件目录就行了

notice：由于页面可以翻页，翻页是通过pn参数实现的，每次加20(每页有20张图)，所以第一页pg为0，第二页为20，以此类推，改一下第19行的内容就可以翻到你想翻的页数了

问题:我的代码有点问题，就是只能爬60张图片，原因未知。。。

import requests
import re
import time

def getHTML(url, kv, headers):
    try:
        r = requests.get(url, params = kv, headers = headers)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def parse(k):
    url = 'https://image.baidu.com/search/flip'
    t = 0
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'}
    start_time = time.time()
    for pages in range(0, 510, 20):
        kv = {'word':k, 'tn':'baiduimage', 'pn':pages}    
        html = getHTML(url, kv, headers)
        if (html):    
            Res = re.findall('"objURL":"(.*?)",', html)
            for url in Res:
                try:
                    r = requests.get(url, headers = headers, timeout = 10)
                    t += 1
                    #这里是要保存的文件路径
                    with open('E:/Python/spider/Project/GetPicture/Picture/' + str(t) + '.jpg', 'wb') as f:
                        f.write(r.content)
                    print('爬取第{}个图片成功'.format(t))
                except:
                    print('爬取图片失败')
                    continue
    end_time = time.time()
    print('Total time:{}s'.format(end_time - start_time))

def main():
    k = input('Please input keywords of the pictures you wanna get:')
    parse(k)

if __name__ == '__main__':
    main()