20214335李佳俊 实验四《Python程序设计》报告

import requests as rq
import json
import time
import os
count = 1
#dao'ku
def crawl(page):
    global count
    if not os.path.exists('nba'):
        os.mkdir('nba')
    url = 'https://image.baidu.com/search/acjson?'
    header = {
        # 'Referer': 'https://image.baidu.com/search/index?ct=201326592&cl=2&st=-1&lm=-1&nc=1&ie=utf-8&tn=baiduimage&ipn=r&rps=1&pv=&fm=rs4&word',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'
    }
    param = {
    "tn": "resultjson_com",
    "logid": "11007362803069082764",
    "ipn": "rj",
    "ct": "201326592",
    "is": "",
    "fp": "result",
    "queryWord": "NBA",
    "cl": "2",
    "lm": "-1",
    "ie": "utf-8",
    "oe": "utf-8",
    "adpicid": "",
    "st": "-1",
    "z": "",
    "ic": "",
    "hd": "",
    "latest": "",
    "copyright": "",
    "word": "NBA",
    "s": "",
    "se": "",
    "tab": "",
    "width": "",
    "height": "",
    "face": "0",
    "istype": "2",
    "qc": "",
    "nc": "1",
    "fr": "",
    "expermode": "",
    "force": "",
    "pn": page,
    "rn": "30",
    "gsm": "1e",
    "1615565977798": "",
    }
    response = rq.get(url, headers=header, params=param)
    result = response.text
    # print(response.status_code)
    j = json.loads(result)
    # print(j)
    img_list = []
    for i in j['data']:
        if 'thumbURL' in i:
            # print(i['thumbURL'])
            img_list.append(i['thumbURL'])
    # print(len(img_list))

    for n in img_list:
        r = rq.get(n, headers=header)
        with open(f'nba/{count}.jpg', 'wb') as f:
            f.write(r.content)
        count += 1


if __name__ == '__main__':
    for i in range(30, 601, 30):
        t1 = time.time()
        crawl(i)
        t2 = time.time()
        t = t2 - t1
        print('page {0} is over!!!  耗时{1:.2f}秒！'.format(i//30, t))