Python实现爬取豆瓣TOP250带GUI版

jin2025

基于requests和PySide6实现

[Python] 纯文本查看 复制代码

import re
import requests
import webbrowser
from PySide6.QtWidgets import QApplication, QMainWindow, QPushButton, QLineEdit, QMessageBox, QTableWidget, \
    QTableWidgetItem
from PySide6.QtCore import Qt


class Stats(QMainWindow):
    def __init__(self):
        super().__init__()
        self.resize(700, 400)
        self.move(300, 300)
        self.setWindowTitle('查询豆瓣Top250')

        self.textEdit = QLineEdit(self)
        self.textEdit.setPlaceholderText("请输入要查询的页码")
        self.textEdit.move(10, 25)
        self.textEdit.resize(150, 30)

        self.button = QPushButton('查询', self)
        self.button.move(185, 25)
        self.button.clicked.connect(self.handle_search)

        # 创建表格并添加到窗口
        self.table = QTableWidget(self)
        self.table.move(10, 75)
        self.table.resize(680, 300)
        self.table.setColumnCount(5)  # 设置列数
        self.table.setHorizontalHeaderLabels(['电影名称', '年份', '评分', '评价人数', 'URL'])  # 设置列标题
        self.tableHeader = self.table.horizontalHeader()
        self.tableHeader.setStretchLastSection(True)

        # 设置表格不可编辑
        self.table.setEditTriggers(QTableWidget.NoEditTriggers)

        # 连接单元格点击信号
        self.table.cellClicked.connect(self.open_url)

    def handle_search(self):
        text = self.textEdit.text()
        url = r'https://movie.douban.com/top250?start=' + text + '&filter='
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0"
        }

        try:
            response = requests.get(url, headers=headers)
            response.encoding = "utf-8"

            obj = re.compile(r'<div class="item">.*?<a href="(?P<url>.*?)">'
                             r'.*?<span class="title">(?P<name>.*?)</span>'
                             r'.*?<br>\s*(?P<year>.*?) / '
                             r'.*?<span class="rating_num" property="v:average">(?P<score>.*?)</span>'
                             r'.*?<span>(?P<num>.*?)人评价</span>', re.S)
            result = obj.findall(response.text)
            rows = len(result)

            self.table.setRowCount(rows)  # 设置行数

            for row, item in enumerate(result):
                self.table.setItem(row, 0, QTableWidgetItem(item[1].strip()))  # 电影名称
                self.table.setItem(row, 1, QTableWidgetItem(item[2]))  # 年份
                self.table.setItem(row, 2, QTableWidgetItem(item[3]))  # 评分
                self.table.setItem(row, 3, QTableWidgetItem(item[4]))  # 评价人数
                self.table.setItem(row, 4, QTableWidgetItem(item[0]))  # URL

                # 设置对齐方式为居中
                for col in range(5):  # 所有列
                    cell_item = self.table.item(row, col)
                    cell_item.setTextAlignment(Qt.AlignHCenter | Qt.AlignVCenter)

            QMessageBox.information(
                self,
                '操作成功',
                f'成功查询 {rows} 条数据。')

        except Exception as e:
            QMessageBox.critical(self, '错误', f'查询失败: {str(e)}')

    def open_url(self, row, column):
        if column == 4:  # 检查是否在 URL 列
            url = self.table.item(row, column).text()
            if url:  # 确保 URL 不为空
                webbrowser.open(url)  # 打开浏览器


app = QApplication([])
stats = Stats()
stats.show()
app.exec()

jin2025

输入需要爬取的页码即可

hsq123456HSQ

哈哈，现学现用，我抄了

mytomsummer

感谢分享学习了

joythinker

学习了，，，，

Velociraptor

长经验了

pO52jie6293

感谢大佬，学习了

Zero0fBegin

感谢分享学习了

hbyhzx

感谢分享。

zsp20250313

学习，已阅