首先打开豆瓣电影排行榜 - 动作电影
然后输入如下代码,用来下载豆瓣电影第一页的电影
# get请求
# 获取豆瓣电影第一页的数据,并且保存起来
import urllib.request
url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=20&limit=20'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 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')
print(content)
# 3 数据下载到本地
# open方法默认情况下使用gbk编码,如果想要写汉字,需要在open方法中指定编码格式为utg-8
fp = open('douban.json', 'w',encoding='utf-8')
fp.write(content)
# 也可以使用如下方法输出到文件中
with open('douban1.json', 'w', encoding='utf-8') as fp:
fp.write(content)
对上述代码进行封装,获取排行榜前十页的数据:
# 豆瓣电影的排行榜前三页url如下:
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=0&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=20&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=40&limit=20
# page 1 2 3 4
# start 0 20 40 60
# start (page - 1) * 20
# 下载豆瓣电影前十页的数据
# 1 请求对象定制
# 2 获取响应数据
# 3 下载数据
import urllib.parse
import urllib.request
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
}
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/97.0.4692.99 Safari/537.36'
}
request = urllib.request.Request(url = url, headers = headers)
return request
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)
# 程序入口
if __name__ == '__main__':
start_page = int(input('请输入起始页码'))
end_page = int(input('请输入结束的页面'))
for page in range(start_page, end_page + 1):
print(page)
# 请求对象定制
request = create_request(page)
# 获取响应的数据
content = get_content(request)
# 下载
down_load(page, content)