运动汇专业的比赛管理平台数据获取_怎样可以把竞彩足球历史数据导出来-优快云博客

本文链接：https://blog.youkuaiyun.com/a494665/article/details/143808032

在获取到运动汇的网站链接后，界面如图所示:

右键检查，我们会发现没有任何数据，只有当我们点开这些"第一单元"、"第二单元"等，数据才会加载出来；

由于我们只需要分析这一个网页并获取其中的数据，所以我们可以简单的手动点开所有这些"单元"以及里面的各个项目的比赛数据，让网站将数据全部加载出来,如下所示:

紧接着，直接利用浏览器! 右键检查:

点击最上面的<html>, 右键移动到复制, 点击复制元素:

自主将这里面的html内容复制到某个文本文件中，随后使用Xpath表达式即可轻松解析出数据，解析代码如下：

from lxml import etree
from re import match


class ReadHtmlTable(object):
    def __init__(self, html_content: str):
        self.html_content = html_content
        self.table_col = ("比赛时间", "项目", "姓名", "学院", "组/道", "名次", "成绩", "得分", "备注")
        

    def get_different_units(self) -> list[etree.Element]:
        tree = etree.HTML(self.html_content)
        units = tree.xpath(r'//*[@id="div_Result"]/ul/li')
        return units

    def get_all_tables(self) -> list[etree.Element]:
        units = self.get_different_units()
        tables = []
        for unit in units:
            table = unit.xpath(r"./div[2]/div/div/table/tbody")
            tables.extend(table)

        return tables

    def get_event_name(self, table_element: etree.Element) -> str:
        # 分条件判断，获取特殊的项目名称
        event_element = table_element.xpath("./tr[1]/td[1]")[0]
        text = etree.tostring(event_element, method='text', encoding='unicode').strip()
        event_slice = [i for i in text.split('\xa0') if i != '']
        match len(event_slice):
            case 3: return event_slice[1]
            case 4: return f"{event_slice[1]}{event_slice[2]}"
            case _: return f"{event_slice[1]}-{event_slice[3]}"

    def get_remarks(self, row_element: etree.Element):
        # 获取备注, 因为有的备注藏在font里头
        remark_element: etree.Element = row_element.xpath(r"./td[7]")[0]
        remark = remark_element.text
        if isinstance(remark, str):
            remark = remark.strip()
        if remark is None or remark == "":
            other_remark = remark_element.xpath(r'./font')
            if len(other_remark) == 0:
                return ''
            return other_remark[0].text
        else:
            return remark
        
    def get_table_record(self, table_element: etree.Element) -> tuple[str, list[tuple]]:
        # 一条记录be like: [None, '2/4', 'XX', '日语', '16.97', '27', None, None]
        rows = table_element.xpath("./tr[2]/td/table/tbody/tr")[1:]
        records = []
        try:
            # 如果是空表就跳出
            event_name = self.get_event_name(table_element)
            print(event_name)
        except IndexError:
            return records
        for rank, row in enumerate(rows, 1):
            # ("比赛年份", "项目", "姓名", "学院", "组/道", "名次", "成绩", "得分", "备注")
            items = [i.text.strip().replace(",", "、") if i.text is not None else "" for i in row.xpath(r"./td")]
            record = (EVENT_YEAR, event_name, items[2], items[3], items[1], rank, items[4], items[5], self.get_remarks(row))
            records.append(record)

        return records

    def write_in_csv(self) -> None:
        with open("./sports_meeting_res.csv", "w", encoding="utf-8") as f:
            f.write(",".join(self.table_col) + "\n")
            for table in self.get_all_tables():
                for record in self.get_table_record(table):
                    # 将记录转换为字符串并写入文件
                    csv_line = ",".join(map(str, record)) + "\n"
                    f.write(csv_line)



if __name__ == "__main__":
    EVENT_YEAR = "2023.11.24-25"
    with open("./sports_meeting_res.txt", "r", encoding="utf-8") as f:
        html_content = f.read()
    read_html_table = ReadHtmlTable(html_content)
    read_html_table.write_in_csv()

需要注意上述代码中, 全局变量EVENT_YEAR是指代比赛年份，需要你自己修改成比赛的真实年份；此外，你需要修改读取的文件路径，在代码中是"./sports_meeting_res2024.txt", 里面是我复制下来的html元素内容；

最后，所有内容就会按照指定格式保存成csv文件！非常Easy啊