爬取哔哩哔哩弹幕并绘制折线图

本文来源吾爱破解论坛

本帖最后由 麦田孤望者 于 2020-1-28 18:45 编辑

这几天实在是太闲了...于是码了一个爬弹幕的程序
用的第三方库有: requests , pysimplegui , matplotlib
版本：一定是3.8 因为我有第42行用了海象操作符...当然那里改成return (cid_tuple,part,re.findall(re.compile('aid=\d{8}',re.S),url)[0][-8:])应该也是没问题的

生成效果

Figure_5.png (130.07 KB, 下载次数: 0)

Figure_4.png (129.92 KB, 下载次数: 0)

下载附件  保存到相册

2020-1-28 18:45 上传

import json
import os
import re
import sys
import time
from fnmatch import fnmatch

import matplotlib.pyplot as plt
import PySimpleGUI as sg
import requests
from pylab import mpl

mpl.rcParams['font.sans-serif'] = ['SimHei']


def findall(tx1,tx2,tx3):
    return re.findall(re.compile('{}(.*?){}'.format(tx1,tx2),re.S),tx3)
def parse_1(url):
    try:
        aid = findall('https://www.bilibili.com/video/av','?spm_i',url)[0][:-1]
    except IndexError:
        aid = url[-8:]
    aid = re.findall(re.compile('\d{8}',re.S),aid)[0]
    #print('aid:',aid)
    res = requests.get('https://api.bilibili.com/x/player/pagelist?aid={}&jsonp=jsonp'.format(aid))
    cid = res.json()['data'][0]['cid']
    #print('cid:',cid)
    return (cid)
    
def parse_2(url):
    
    
    cid_tuple = []
    part=[]
    res = requests.get(url)
    html = findall('window.__kanzaki_ranko=','</script>',res.text)[0]
    cid_list = json.loads(html)['main']['pages']
    #rint(cid_list)
    for i in cid_list:
        cid_tuple.append(i['cid'])
        part.append(i['part'])
    return (cid_tuple,part,aid:=re.findall(re.compile('aid=\d{8}',re.S),url)[0][-8:])

def parse_3(url):
    cid_list=[]
    title_list=[]
    res = requests.get(url).text
    html=findall('.__INITIAL_STATE__=',';\(function\(\)',res)[0]
    a = json.loads(html)['epList']
    for i in a:
        cid_list.append(i['cid'])
        title_list.append(i['titleFormat']+' '+i['longTitle'])
    return (cid_list,title_list,'')

def check(url,mode=''):
    
    if fnmatch(url,'https://www.bilibili.com/*') == False:
        print('请输入正确视频地址！')
        sys.exit()
    if fnmatch(url,'https://www.bilibili.com/video/*') == True:
        #print('1')
        return parse_1(url)
    elif fnmatch(url,'https://www.bilibili.com/blackboard/*') == True:
        #print('2')
        return parse_2(url)
    elif fnmatch(url,'https://www.bilibili.com/bangumi/*') == True:
        #print('3')
        return parse_3(url)
    

def get_comment(cid):
    list1=[]
    list2=[]
    #print(cid)
    res = requests.get('http://comment.bilibili.com/{}.xml'.format(cid))
    res.encoding='utf-8'
    comment_list = findall('<d','</d>',res.text)
   
    for i in comment_list:
        #print(i)
        params = findall('p="','">',i)[0]
        value = re.sub(params+'">','',i)[4:]
        params = params.split(',')
        list1.append(params)
        list2.append(value)
    a=(list1,list2)

    return(a)
    
def check_again(tup,url):

    layout=[]
    if str(type(tup))=="<class 'tuple'>":
        cid=tup[0]
        for i,v in enumerate(tup[1]):
            layout.append([sg.Button(v,font='宋体.ttf')])
            
        window2 = sg.Window('请确认第几话',layout=layout)
        a,b = window2.Read()
        
        for q,r in enumerate(tup[1]):
            if a == r:
                break

        anw = q
        window2.close()
        if int(anw) != i+1:
            cid = [str(tup[0][int(anw)])]
        
        title=str(tup[1][int(anw)])
       
        
    else:
        res = requests.get(url)
        html=findall('<div id="viewbox_report" class="video-info report-wrap-module report-scroll-module">','class="video-title">',res.text)[0]
        title=findall('title="','"',html)[0]
        cid=[tup]
    return (cid,title)

def main():
    global video_url
    tx1 = sg.Text('视频链接：',font='宋体.ttf')
    txt = sg.Input('')
    bt1 = sg.Button('确定',font='宋体.ttf')
    window = sg.Window('哔哩哔哩弹幕',layout=[[tx1,txt,bt1]])
    a,b = window.Read()

    
    video_url = b[0]
    window.close()
    cid = check_again(check(video_url),video_url)
    for i in cid[0]:
        a= get_comment(int(i))
        
    title=cid[1]
    
    return (a,title)
def bubbleSort(arr):
    n = len(arr)
 
    
    for i in range(n):
 
       
        for j in range(0, n-i-1):
           
 
            if arr[j][0] > arr[j+1][0] :
                arr[j], arr[j+1] = arr[j+1], arr[j]
    return arr

 


def draw_():
    mai=main()
    x,y=mai[0][0],mai[0][1]
    title=mai[1]
    list1=[]
    list2=[]
    for rr,i in enumerate(x):
        list1.append((int(float(i[0])),y[rr]))
    list2=bubbleSort(list1)
    
    max_time=list2[-1:][0][0]
    len_lis=len(list2)
    if max_time <=500:
        e = 10
    elif max_time >500:
        e=30
    elif max_time >1000:
        e=120
    elif max_time >3000:
        e=300
    a = max_time//e
    b = max_time%e
    c = a+1
   
    list3=[]
    list4=[]
    d=0
    for i in range(a):
        lambda_=[]
        for ii in list2:
            if i*e<ii[0]<=i*e+e:
                lambda_.append(ii)
        list3.append(len(lambda_))
        list4.append(i*e)
        d+=len(lambda_)
    
    list3.append(len_lis-d)
    list4.append(max_time)

  
    x = range(len(list4))
    plt.figure(figsize=(len(list4)-6,6.5))
    plt.plot(x, list3, marker='o', mec='r', mfc='w',label=u'弹幕数量曲线图')

    plt.legend() # 让图例生效
    plt.xticks(x, list4, rotation=20)
    plt.margins(0)
    plt.subplots_adjust(bottom=0.15)
    plt.xlabel(u"时间/s ") #X轴标签
    plt.ylabel("数量") #Y轴标签
    plt.title(title) #标题
 
    plt.show()
    
if __name__ == '__main__':
    try:
        draw_()
    except BaseException as e:
        print('ERROR:',e)

Figure_5.png (130.07 KB, 下载次数: 0)

下载附件  保存到相册

2020-1-28 18:44 上传