爬虫

最新推荐文章于 2024-10-05 08:57:27 发布

朝夕zxzx

最新推荐文章于 2024-10-05 08:57:27 发布

阅读量126

点赞数

本文链接：https://blog.csdn.net/zhaoxizxzx/article/details/113852533

版权

python

import urllib.request, urllib.error   # 制定url，获取网页数据
import json
import time


url = "https://api.bilibili.com/x/relation/stat?vmid=66607740"
head = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36 Edg/88.0.705.63"
    }
 # 封装
req = urllib.request.Request(url=url, headers=head)
s = ""
response = urllib.request.urlopen(req)
s = response.read().decode("utf-8")
follower = json.loads(s).get("data").get("follower") # 转换json
t2 = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) # 当前时间

# 爬取多页
baseurl = 'https://movie.douban.com/subject/1295644/reviews?start='
for i in range(255):
	url = baseurl + str(i*20)