Python编程实现下载器自动爬取采集B站弹幕示例

import requests
import re
from PyQt5.QtWidgets import *
from PyQt5 import QtCore
from PyQt5.QtGui import *
from PyQt5.QtCore import QThread, pyqtSignal
from bs4 import BeautifulSoup

    def __init__(self,parent =None):
        super(Ui_From,self).__init__(parent=parent)
        self.setWindowTitle("B站弹幕采集")
        self.setWindowIcon(QIcon('pic.jpg'))# 图标
        self.top_label = QLabel("作者：小张\n 微信公号：小张Python")
        self.top_label.setAlignment(QtCore.Qt.AlignHCenter)
        self.top_label.setStyleSheet('color:red;font-weight:bold;')
        self.label = QLabel("B站视频url")
        self.label.setAlignment(QtCore.Qt.AlignHCenter)
        self.editline1 = QLineEdit()
        self.pushButton = QPushButton("开始下载")
        self.pushButton.setEnabled(False)#关闭启动
        self.Console = QListWidget()
        self.saveButton = QPushButton("保存至")
        self.layout = QGridLayout()
        self.layout.addWidget(self.top_label,0,0,1,2)
        self.layout.addWidget(self.label,1,0)
        self.layout.addWidget(self.editline1,1,1)
        self.layout.addWidget(self.pushButton,2,0)
        self.layout.addWidget(self.saveButton,3,0)
        self.layout.addWidget(self.Console,2,1,3,1)
        self.setLayout(self.layout)
        self.savepath = None
        self.pushButton.clicked.connect(self.downButton)
        self.saveButton.clicked.connect(self.savePushbutton)
        self.editline1.textChanged.connect(self.syns_lineEdit)

 def syns_lineEdit(self):
        if self.editline1.text():
            self.pushButton.setEnabled(True)#打开按钮

  def savePushbutton(self):
        savePath = QFileDialog.getSaveFileName(self,'Save Path','/','txt(*.txt)')
        if savePath[0]:# 选中 txt 文件路径
            self.savepath  = str(savePath[0])#进行赋值

f = open(self.savepath, 'w+', encoding='utf-8')  # 打开 txt 文件
        res = requests.get(url)
        res.encoding = 'utf-8'
        soup = BeautifulSoup(res.text, 'lxml')
        items = soup.find_all('d')  # 找到 d 标签
        for item in items:
            text = item.text
            f.write(text)
            f.write('\n')
        f.close()

class Parsetext(QThread):
    trigger = pyqtSignal(str) # 信号发射；
    def __init__(self,text,parent = None):
        super(Parsetext,self).__init__()
        self.text = text
    def __del__(self):
        self.wait()
    def run(self):
        print('解析 -----------{}'.format(self.text))
        result_url = re.findall('.*?"baseUrl":"(.*?)","base_url".*?', self.text)[0]
        self.trigger.emit(result_url)