爬取b站up主投稿视频的八项数据

---

前言

爬取b站up主投稿视频的八项数据，代码中限制了只爬取2023年的视频

---

代码

import json
from time import sleep

import requests
from selenium import webdriver
from selenium.common import NoSuchElementException
from selenium.webdriver.common.by import By
import pandas as pd


def get_info(BV):
    base_url = f'https://api.bilibili.com/x/web-interface/view?bvid={BV}'
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'}
    r = requests.get(base_url, headers=header)  # 获取网页的信息

    _json_data = json.loads(r.text)  # 将数据进行格式转换，这样方便处理
    #合作
    menbers= _json_data.get('data').get('staff')
    pep=" "
    if menbers!=None:
        for menber in menbers:
            pep=pep+menber['title']+":"
            pep=pep+menber['name']+" "

    view = _json_data.get('data').get('stat').get('view')#播放量
    danmaku = _json_data.get('data').get('stat').get('danmaku')#弹幕
    reply = _json_data.get('data').get('stat').get('reply')#评论
    favorite = _json_data.get('data').get('stat').get('favorite')#收藏
    coin = _json_data.get('data').get('stat').get('coin')#投币
    share = _json_data.get('data').get('stat').get('share')#转发
    like = _json_data.get('data').get('stat').get('like')#点赞
    return [view,danmaku,reply,favorite,coin,share,like,pep]

driver = webdriver.Edge()

driver.get(r'https://space.bilibili.com/488055582/video?tid=0&pn=9&keyword=&order=pubdate')
data=[]
f=True
while f:
    main_window_handle = driver.current_window_handle
    # 定位指定元素
    elements = driver.find_elements(By.CLASS_NAME,"small-item.fakeDanmu-item")
    for element in elements:
        if "2022" in element.find_element(By.CLASS_NAME, "time").text:
            f=False
            break
        if "2023" in element.find_element(By.CLASS_NAME,"time").text:
            time = element.find_element(By.CLASS_NAME,"time").text
            title = element.find_element(By.CLASS_NAME,"title").text
            length = element.find_element(By.CLASS_NAME,"length").text
            try:
                element.find_element(By.CLASS_NAME, "be-tags-container")
                hz=True
            except:
                hz=False

            info = get_info(element.get_attribute("data-aid"))
            info.extend([title,time,length])
            data.append(info)



    driver.find_element(By.CLASS_NAME, "be-pager-next").click()
    sleep(2)




sleep(5)
driver.close()

df = pd.DataFrame(data=data, columns=["播放量","弹幕","评论","收藏","投币","转发","点赞","合作","标题","发布时间","时长"])
df.to_excel("result.xlsx")