代码
import urllib.parse
import urllib.request
# 请求对象的定制
def get_request(page):
base_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&'
# 找规律
data = {
"start": (page - 1) * 20,
"limit": 20
}
data = urllib.parse.urlencode(data)
url = base_url + data
# 第一个反爬 UA
headers = {
'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.0.0"
}
request = urllib.request.Request(url=url, headers=headers)
return request
# 获取内容
def get_content(request):
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
return content
# 打印到本地
def Content_Download(page, content):
with open("DB第" + str(page) + "页.json", "w", encoding='utf-8') as f:
f.write(content)
# 规律
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):
request = get_request(page) # 请求对象的定制
content = get_content(request) # 获取内容
Content_Download(page, content) # 打印到本地
URL来源如下图
(1)Db motion picture空白处右键检查
(2)点击网络然后刷新,找到下图名称,请求URL为代码url
UA来源如下图
爬取成功截图