爬取B站评论区

# 开发时间：2022/2/22 10:38
import requests
import json
import os
table = 'fZodR9XQDSUm21yCkr6zBqiveYah8bt4xsWpHnJE7jL5VG3guMTKNPAwcF'
tr = {}
for i in range(58):
    tr[table[i]] = i
s = [11, 10, 3, 8, 4, 6]
xor = 177451812
add = 8728348608

samename = {}
samefan = {}

def dec(x): # decoding,BV转化为AV号
    r = 0
    for i in range(6):
        r = r+tr[x[s[i]]]*58**i
    return (r-add)^xor

def getComment(Bvid, page):
    Avid = dec(Bvid)
    url = "https://api.bilibili.com/x/v2/reply?pn=" + str(page) +  "&type=1&oid=" + str(Avid) + "&sort=2"
    data = requests.get(url)
    content = json.loads(data.text)
    return content['data']['replies']

BVID = "BV1P5411Z7YU"
page = 1        # 需要爬的评论区页数，1页有20条评论

with open('评论.txt', 'w', encoding = 'utf-8') as f:
    for pg in range(1, int(page) + 1):
        commonComment = getComment(BVID, pg)
        commentLength = len(commonComment)
        for index in range(commentLength):
            if commonComment[index]['member']['user_sailing']['cardbg']:
                f.write('第'+str(pg)+'页第'+str(index+1)+'条'+'\t'+commonComment[index]['member']['uname']+'\t'+commonComment[index]['member']['user_sailing']['cardbg']['name']+':\n')
                if commonComment[index]['member']['user_sailing']['cardbg']['name'] in samefan:
                    samefan[commonComment[index]['member']['user_sailing']['cardbg']['name']] += 1
                else:
                    samefan.setdefault(commonComment[index]['member']['user_sailing']['cardbg']['name'], 1)
            else:
                f.write('第' + str(pg) + '页第' + str(index + 1) + '条' + '\t' + commonComment[index]['member']['uname'] + ':\n')
            if commonComment[index]['member']['uname'] in samename:
                samename[commonComment[index]['member']['uname']]+=1
            else:
                samename.setdefault(commonComment[index]['member']['uname'], 1)

            f.write(commonComment[index]['content']['message']+'\n')

with open('评论详情.txt', 'w', encoding = 'utf-8') as f:
    for i in samename.keys():
        #print(i+'\t', samename[i])
        f.write(i+'\t'+str(samename[i])+'\n')

with open('牌子详情.txt', 'w', encoding='utf-8') as f:
    for i in samefan.keys():
        #print(i+'\t', samename[i])
        f.write(i+'\t'+str(samefan[i])+'\n')

 

原代码来源于b站的一个up的视频，这里是根据那个代码小小改动了一下