B站评论采集

B站评论采集

打开目标网址

哔哩哔哩 (゜-゜)つロ 干杯~-bilibili

找到爬取得剧的评论，打开浏览器抓包工具进行抓包分析：

这里爬取鬼灭之刃第一季的评论数据，

分析网页

打开评论页面，可以看到分为短评（128702）和长评（639）条。常规操作直接F12打开网络观察发送的请求数据。

在评论页面往下翻几下就可以看到有个url是“list?“开头的，点开预览果然就是哔哩哔哩评论的api了。找到了api就很好办了，直接分析一下api的组成和需要传递的参数。

分析b站api

 复制代码 隐藏代码
https://api.bilibili.com/pgc/review/short/list?media_id=22718131&ps=20&sort=0&cursor=83215035767195

观察一下链接，有个short字段，这个就是对应的短评，如果换成long就是长评。

”ps=20“就是一页的数据。”media_id=22718131“就是番剧的id。

”cursor“字段就是数据的地址，每次请求数据返回的json数据都会有下一页的cursor。

下面就是用requests进行请求写代码

先导入库：

import requests
import json
import time
import csv

爬取代码：

def levels_get(mid, proxies):

    url = f'https://api.bilibili.com/x/space/wbi/acc/info?mid={str(mid)}'
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
        'cookie': "_uuid=B31794AC-389B-5ABE-431A-4A457532710F563197infoc; buvid3=90E810B6-24C7-0FD9-FCEB-FFAAD82CE42266124infoc; b_nut=1666688064; buvid4=C5894024-2549-4CC5-B6CC-4CE4F3C6025F66124-022102516-ueloTil9hhszmIQpPi1hPg==; buvid_fp_plain=undefined; i-wanna-go-back=-1; nostalgia_conf=-1; rpdid=|(u))umkR)l|0J'uYY)Y~lkkl; bsource=search_google; LIVE_BUVID=AUTO2616698028069789; is-2022-channel=1; CURRENT_BLACKGAP=0; CURRENT_FNVAL=4048; CURRENT_QUALITY=120; fingerprint=5fdc996e8cc80fd6b9c56ffc54ce7181; sid=8dtevv76; bp_video_offset_83512806=744605732851155000; buvid_fp=5fdc996e8cc80fd6b9c56ffc54ce7181; b_lsid=F72104910B_18557CE9216; b_ut=7; innersign=1; PVID=8",
    }
    try:
        rs = requests.get(url, headers=header,proxies=proxies)
    except:
        proxies = gengxin()

        rs = requests.get(url, headers=header, proxies=proxies, timeout=10)
    datad = json.loads(rs.text)
    try:
        return datad['data']['level']
    except:
        return 'Nah'

cursor = 78670930957092
while cursor != '老6':
    url = f'https://api.bilibili.com/pgc/review/long/list?media_id=22718131&ps=20&sort=0&cursor={cursor}'
    print(url)
    while True:
        try:
            r = requests.get(url, timeout=5)
            data = json.loads(r.text)
            break
        except:
            print('请求超时')
            time.sleep(1)

    for i in data['data']['list']:
        uname = i['author']['uname']#用户昵称
        userid = i['author']['mid']#用户id
        score = i['score']#用户评分
        content = i['content']#用户评论内容
        time_unix = int(i['mtime'])
        times = timefun(time_unix)
        # middd = levels_get(userid, proxies)
        middd = 'Nah'
        print(times, uname, userid, middd, score, content)
        with open("test.csv", "a", newline='',encoding='UTF8') as csvfile:
            writer = csv.writer(csvfile)
            # 写入多行用writerows
            writer.writerow([times, uname, userid, middd, score, content])

    cursor = data['data']['next']
    print(f'下一个页面{cursor}')

完整代码：

import requests
import json
import time
import csv

'''包括评分用户id及会员等级、具体评分星级、长评以及短评的评论内容、评分时间，'''

def timefun(time1):
    time1 = int(time1)
    timeArray = time.localtime(time1)
    times = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)  # 时间
    return times

def levels_get(mid, proxies):

    url = f'https://api.bilibili.com/x/space/wbi/acc/info?mid={str(mid)}'
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
        'cookie': "_uuid=B31794AC-389B-5ABE-431A-4A457532710F563197infoc; buvid3=90E810B6-24C7-0FD9-FCEB-FFAAD82CE42266124infoc; b_nut=1666688064; buvid4=C5894024-2549-4CC5-B6CC-4CE4F3C6025F66124-022102516-ueloTil9hhszmIQpPi1hPg==; buvid_fp_plain=undefined; i-wanna-go-back=-1; nostalgia_conf=-1; rpdid=|(u))umkR)l|0J'uYY)Y~lkkl; bsource=search_google; LIVE_BUVID=AUTO2616698028069789; is-2022-channel=1; CURRENT_BLACKGAP=0; CURRENT_FNVAL=4048; CURRENT_QUALITY=120; fingerprint=5fdc996e8cc80fd6b9c56ffc54ce7181; sid=8dtevv76; bp_video_offset_83512806=744605732851155000; buvid_fp=5fdc996e8cc80fd6b9c56ffc54ce7181; b_lsid=F72104910B_18557CE9216; b_ut=7; innersign=1; PVID=8",
    }
    try:
        rs = requests.get(url, headers=header,proxies=proxies)
    except:
        proxies = gengxin()

        rs = requests.get(url, headers=header, proxies=proxies, timeout=10)
    datad = json.loads(rs.text)
    try:
        return datad['data']['level']
    except:
        return 'Nah'

cursor = 78670930957092
while cursor != '老6':
    url = f'https://api.bilibili.com/pgc/review/long/list?media_id=22718131&ps=20&sort=0&cursor={cursor}'
    print(url)
    while True:
        try:
            r = requests.get(url, timeout=5)
            data = json.loads(r.text)
            break
        except:
            print('请求超时')
            time.sleep(1)

    for i in data['data']['list']:
        uname = i['author']['uname']#用户昵称
        userid = i['author']['mid']#用户id
        score = i['score']#用户评分
        content = i['content']#用户评论内容
        time_unix = int(i['mtime'])
        times = timefun(time_unix)
        # middd = levels_get(userid, proxies)
        middd = 'Nah'
        print(times, uname, userid, middd, score, content)
        with open("test.csv", "a", newline='',encoding='UTF8') as csvfile:
            writer = csv.writer(csvfile)
            # 写入多行用writerows
            writer.writerow([times, uname, userid, middd, score, content])

    cursor = data['data']['next']
    print(f'下一个页面{cursor}')