get请求（豆瓣电影前五页爬取）

前提：

第一页url

https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=0&limit=20

第二页url

https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=20&limit=20

第三页url

https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=40&limit=20

观察得出每页的url中得start发生了变化

---

（一）获取的页数

    start_page = int(input("请输入起始的页码："))
    end_page = int(input("请输入结束的页码："))
    for page in range(start_page, end_page + 1):
        print(page)

• python基础知道range（）左闭右开

（二）每一页的请求对象的定制

def create_request(page):
    base_url = ("https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&")

    data = {
        'start': (page - 1) * 20,
        'limit': 20
    }

    # start = 60 & limit = 20  获得&符号
    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/129.0.0.0 Safari/537.36"
    }

    request = urllib.request.Request(url=url, headers=headers)

    return request

需要拼接url

    base_url = "https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&"

    data = {
        'start': (page - 1) * 20,
        'limit': 20
    }

    # start = 60 & limit = 20  获得&符号
    data = urllib.parse.urlencode(data)

    url = base_url + data

（三）获得响应数据

def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode("utf-8")
    return content

（四） 下载数据

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

（五）完整代码

import urllib.parse
import urllib.request


#  每一页的请求对象的定制
def create_request(page):
    base_url = ("https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&")

    data = {
        'start': (page - 1) * 20,
        'limit': 20
    }

    # start = 60 & limit = 20  获得&符号
    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/129.0.0.0 Safari/537.36"
    }

    request = urllib.request.Request(url=url, headers=headers)

    return request


#  获得响应数据
def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode("utf-8")
    return content


#  下载数据
def down_load(page, content):
    with open('douban' + str(page) + '.json', 'w', encoding="utf-8") as fp:
        fp.write(content)


if __name__ == '__main__':
    start_page = int(input("请输入起始的页码："))
    end_page = int(input("请输入结束的页码："))
    for page in range(start_page, end_page + 1):
        print(page)
        #  每一页的请求对象的定制
        request = create_request(page)
        #  获得响应数据
        content = get_content(request)
        #  下载数据
        down_load(page, content)

（六）结果

---

努力中。。。