教你用 Python 快速获取相关概念股，辅助价值投资！

import requests
from lxml import etree
import re

...
 def __get_concept_stocks_info(self):
        """
        获取概念股信息
        :return:
        """
        html_element = etree.HTML(self.session.get(self.home_url).text)
        a_elements = html_element.xpath('//p[@class="jrj-clear"]//a')

        result = []

        for a_element in a_elements:
            a_element_text = a_element.xpath('./text()')[0].replace('概念股', '')
            a_element_href = a_element.xpath('./@href')[0]

            if self.keyword in a_element_text:
                a_element_tag = re.findall(r'^.*_(.*).shtml$', a_element_href)[-1]
                result.append({
                    "cs": a_element_text,
                    "href": a_element_href,
                    "tag": a_element_tag
                })
        return result
...

...
    def __get_concept_stocks(self, concept_stocks_info):
        """
        获取相关概念股列表
        :param concept_stocks_info:
        :return:
        """
        url = f'http://**/concept/conceptdetail/conceptStock_{concept_stocks_info.get("tag")}.js'
        headers = {'User-Agent': UserAgent().random}
        # 去掉换行符，转为中文
        resp = self.session.get(url, headers=headers).text.replace('\n', '').encode('utf-8').decode(
            'unicode_escape')
        # 正则匹配，获取对应股票
        stocks_list = json.loads(re.findall(r'^.*"stockData":(.*)};$', resp, re.IGNORECASE)[0].replace("\'", "\""))

        return [(item[1], item[0]) for item in stocks_list]
...
        # 2、获取相关概念列表
        for concept_stocks_info in concept_stocks_infos:
            concept_stocks = self.__get_concept_stocks(concept_stocks_info)
            # print('概念个股列表如下：')
            # print(concept_stocks)
...

...
        def __get_stock_info(self, concept_stock):
        """
        获取个股的基本信息
        :return:
        """
        stock_name = concept_stock[0]  # 股票名称
        stock_tag = concept_stock[1]  # 股票编号
        url = self.stock_home.format(stock_tag)

        # 编码问题
        headers = {'User-Agent': UserAgent().random}
        resp = self.session.get(self.stock_url.format(stock_tag, self.__get_time()),
                                headers=headers).text.replace('\n', '')
        # 解析关键数据
        resp_data = json.loads(re.findall(r'^.*HqData:(.*)};$', resp, re.IGNORECASE)[0])[0]
        # print(resp_data)
        # 获取股票关键信息
        stock_price = resp_data[11]  # 实时价格
        # print(stock_price)
        # 获取涨跌
        stock_up_or_down = str(resp_data[19]) + "%"  # 涨跌幅
        # print("涨跌幅：", stock_up_or_down)
        stock_num_ratio = resp_data[22]  # 量比
        # print(stock_num_ratio)
        stock_change_ratio = str(resp_data[24]) + "%"  # 换手率
        # print(stock_change_ratio)
        stock_pe = resp_data[-1]  # 市盈率
        # print(stock_pe)

        return {
            "name": stock_name,
            "no": stock_tag,
            "url": url,
            "price": stock_price,
            "up_or_down": stock_up_or_down,
            "num_ratio": stock_num_ratio,
            "change_ratio": stock_change_ratio,
            "pe": stock_pe
        }
...

...
  # 4、按照市盈利排序(升序)
  stocks.sort(key=lambda x: x["pe"])

  # 5、打印
  print(json.dumps(stocks))
...