python爬取bilibili数据_python爬取bilibili编程区的视频信息

[Asm] 纯文本查看 复制代码import requests

import json

import time

# 网址

url = "https://api.bilibili.com/x/web-interface/search/all/v2"

# 浏览器代{过}{滤}理

headers = {

"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36",

"referer": "https://api.bilibili.com/x/web-interface/search/all/v2?context=&page=1&order=&keyword=%E7%BC%96%E7%A8%8B&duration=&tids_1=&tids_2=&__refresh__=true&highlight=1&single_column=0&jsonp=jsonp&callback=__jp2"

}

# 网页后缀

parameters = {

"context": "",

"page": "3",

"order": "",

"keyword": "编程",

"duration": "",

"tids_1": "",

"tids_2": "",

"__refresh__": "true",

"search_type": "video",

"highlight": "1",

"single_column": "0",

"jsonp": "jsonp",

"callback": "__jp1",

}

# 格式化时间戳 转换成时间格式

def Transformation_time(pud_times):

timearray = time.localtime(pud_times)

format_time = time.strftime("%Y-%m-%d %H:%M:%S", timearray)

return format_time

# 去除数据中的多余的杂乱字符

def data_fromat(data):

limit = ["#", "；", "，", " ", "【", "】", "\n", "\t", '\r' ,'', ""]

# 遍历分隔符 替换成空

for i in limit:

data = data.replace(i, "")

return data

# # 筛选数据并写入

def screening_data(data):

# 每一页的所有数据都在这个数组里

information = data["data"]["result"][8]["data"]

for x in range(len(information)):

with open("d:/bilibili_programming1.txt","a",encoding="utf-8") as file:

file.write(("up主："+information[x]["author"]+"\t"))

file.write(("url："+information[x]["arcurl"]+"\t"))

# 调用data_fromat剔除多余字符

file.write(("标题："+data_fromat(information[x]["title"])+"\t"))

# 调用data_fromat剔除多余字符

file.write(("描述：" + data_fromat(information[x]["description"]) + "\t"))

file.write(("播放量：" + str(information[x]["play"]) + "\t"))

file.write(("弹幕量：" + str(information[x]["video_review"]) + "\t"))

file.write(("收藏量：" + str(information[x]["favorites"]) + "\t"))

file.write(("标签：" + information[x]["tag"] + "\t"))

file.write(("评论量：" + str(information[x]["review"]) + "\t"))

# 转换成时间格式

file.write(("发布日期：" + Transformation_time(information[x]["pubdate"]) + "\n"))

file.write(("时长(分)：" + str(information[x]["duration"]) + "\n"))

if __name__ == '__main__':

for i in range(1, 51):

if i >= 2:

headers["referer"] = "https://api.bilibili.com/x/web-interface/search/all/v2?context=&page="+str(i-1)+"&order=&keyword=%E7%BC%96%E7%A8%8B&duration=&tids_1=&tids_2=&__refresh__=true&highlight=1&single_column=0&jsonp=jsonp&callback=__jp2"

parameters["page"] = i

# 获取的数据转成text然后去除多余字符，再从转成json格式

datas = json.loads((requests.get(url,params=parameters,headers=headers).text).replace("__jp1(","").replace(")",""))

screening_data(datas)

time.sleep(3)