爬虫_urllib中ajax的get请求

1.爬取豆瓣电影第一页数据并下载

#get请求
#获取豆瓣电影的第一页的数据并且保持起来
import urllib.request
url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=0&limit=20'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.67 Safari/537.36'
}
# (1) 请求对象的定制
request = urllib.request.Request(url=url,headers=headers)
# (2) 获取响应的数据
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
# (3) 数据下载到本地
# open方法默认情况下使用的是gbk的编码，如果我们要想保存汉字，那么需要在open方法中制定编码格式为utf-8
# encoding = 'utf-8'
ft = open('douban.json','w',encoding='utf-8')
ft.write(content)

 

2.爬取豆瓣电影前10页数据并下载本地

 经过分析获取请求接口地址：https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=0&limit=20

#get请求
#获取豆瓣电影的前10页的数据并且保持起来
import urllib.request
import urllib.parse
url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=0&limit=20'
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=0&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=20&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=40&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&start=60&limit=20

#page  1  2  3  4
#start 0  20 40 60
#start (page-1)*20

#=======================
#@description:请求对象定制
#@author:tnwner
#@date:2022-05-23 13:19
#======================
def create_request(page):
    base_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&'
    data = {
        'start':(page-1)*20,
        'limit':20
    }
    data = urllib.parse.urlencode(data)
    url = base_url+data
    print(url)
    headers= {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.67 Safari/537.36'
    }
    request = urllib.request.Request(url=url,headers=headers)
    return request
#=======================
#@description:获取响应的数据
#@author:tnwner
#@date:2022-05-23 13:19
#======================
def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

def down_load(page,content):
    with open('douban_' + str(page) + '.json','w',encoding='utf-8') as fp:
        fp.write(content)

if __name__ == '__main__':
    start_input = int(input('请输入起始的页码'))
    end_inout = int(input('请输入结束的页码'))
    for page in range(start_input,end_inout+1):
        #请求对象的定制
        request = create_request(page)
        #获取响应的数据
        content = get_content(request)
        #下载
        down_load(page,content)