#
# made by 杨庆华
import urllib.request
import urllib.parse
import os
import time
fileName = "豆瓣"
#创建文件夹,如果不存在就创建
if not os.path.isdir(fileName):
os.mkdir(fileName)
url = 'https://movie.douban.com/j/chart/top_list?type=13&interval_id=100%3A90&action='
number = 20
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
startPage = int(input("请输入起始页码"))
endPage = int(input("请输入结束页码"))
for page in range(startPage,endPage+1):
form_data = {
'start': (page - 1) * number,
'limit': number,
}
postUrl = urllib.parse.urlencode(form_data).encode()
request = urllib.request.Request(url=url,headers=headers)
response = urllib.request.urlopen(request,postUrl)
# print(response.read().decode())
# 开始写入文件
filePath = fileName+'/'+str(page)+'.html'
with open(filePath,'wb') as fp:
fp.write(response.read())
print("第{0}页已经下载完毕.......".format(page))
time.sleep(2)
爬取豆瓣的json数据
最新推荐文章于 2024-01-10 12:00:00 发布