实战 | 教你快速爬取热门股票，辅助量化交易！

# 安装依赖
pip3 install selenium

pip3 install pandas

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service

chrome_options = Options()
# 无头模式运行
chrome_options.add_argument('--headless')

s = Service(r"C:\work\chromedriver.exe")

browser = webdriver.Chrome(service=s, options=chrome_options)
browser.implicitly_wait(5)

@calc_run_time
def start():
    url = '主页地址'
    browser.get(url)
    browser.maximize_window(

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.keys import Keys

def get_rank_list():
    """
    获取热门股票列表数据
    :return:
    """
    datas = []

    # 股票热度排名
    rank_no = 0

    # 抓取所有数据
    while True:
        # 等待加载完成（显示等待）
        WebDriverWait(browser, 120, 0.5).until(
            EC.presence_of_element_located((By.XPATH, '//*[@class="stock_tbody"]/tr'))
        )

        # 处理数据
        tr_elements = browser.find_elements(By.XPATH, '//*[@class="stock_tbody"]/tr')

        for tr_element in tr_elements:
            name = tr_element.find_element(By.XPATH, './/div[@class="nametd_box"]/a').text
            price = tr_element.find_element(By.XPATH, './/td[7]/div').text
            up_rate = tr_element.find_element(By.XPATH, './/td[9]/div').text  # 涨跌幅度
            stock_home_url = tr_element.find_element(By.XPATH, './/td[4]//a').get_attribute("href")

            rank_no = rank_no + 1

            datas.append({
                "name": name,
                "price": price,
                "up_rate": up_rate,
                "stock_home_url": stock_home_url,
                "rank_no": rank_no,
                "pe": 0.0
            })

        # 点击下一页
        try:
            page_next = browser.find_element(By.XPATH, '//a[contains(text(), "下一页")]')
        except:
            page_next = None

        # 如果是最后一页，就中断
        if page_next:
            page_next.click()
        else:
            break

from selenium.webdriver.common.action_chains import ActionChains

def get_stock_pe(stock_home_url):
    """
    获取股票的动态PE
    :param stock_home_url:
    :return:
    """
    browser.get(stock_home_url)
    browser.maximize_window()

    # 等待加载完成
    WebDriverWait(browser, 120, 0.5).until(
        EC.presence_of_element_located((By.XPATH, '//div[@class="ssy"]//li[5]/span'))
    )

    # PE ICON
    pe_element = browser.find_element(By.XPATH, '//td[@class="n"]/span[@class="title_help"]')
    # 动态PE
    pe_dynamic = browser.find_element(By.XPATH, '//div[@class="brief_info_c"]//tr[1]/td[12]/span/span').text
    # return float(pe)

    # 移动鼠标位置到PE ICON处，展示滚动PE
    ActionChains(browser).move_to_element(pe_element).perform()

    # 获取滚动市盈率
    pe_roll = browser.find_element(By.XPATH, '//span[@class="title_help"]//div[@class="ssy"]//li[5]/span').text

    # 异常处理
    try:
        pe_roll = float(pe_roll)
    except:
        pe_roll = 0.0
    return pe_roll

...
# 获取股票的滚动PE，设置进去
for item in datas:
    item['pe'] = get_stock_pe(item.get("stock_home_url"))
    # 随机休眠
    random_sleep()
...

import random
import time

def random_sleep(mu=1, sigma=0.4):
    """随机睡眠
    :param mu: 平均值
    :param sigma: 标准差，决定波动范围
    """
    secs = random.normalvariate(mu, sigma)
    if secs <= 0:
        secs = mu  # 太小则重置为平均值
    print("休眠时间:", secs)
    time.sleep(secs)

import pandas as pd

# 重命名
code = {"name": "名称", "price": "价格", "up_rate": "涨跌幅", "stock_home_url": "URL", "rank_no": "排名",
        "pe": "动态PE"}
result = pd.DataFrame(datas).rename(columns=code)

# 数据转换
# 将Series列字符串转为Float数据类型
# result["动态PE"] = result["动态PE"].astype(float)

# 过滤出PE为正，且数据小于30的数据
result = result[(0 < result["动态PE"]) & (result["动态PE"] <= 30)]

import pandas as pd

...
# 按PE升序排列，并重新标记索引
result = result.sort_values(by="动态PE", ascending=True, ignore_index=True)

result.to_csv("热门股票排名.csv")
...