python爬取某新闻网页的标题、关键字和时间

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import time
import csv
from selenium.webdriver.chrome.service import Service


# 设置Edge浏览器路径
service = Service(r"D:\python\msedgedriver.exe")#设置你自己下载的msedgedriver路径

# 初始化Edge浏览器
driver = webdriver.Edge(service=service)

# 打开新闻网站
driver.get("https://www.bohe.cn/zx/list/113_1/")

# 创建CSV文件保存数据
csv_file = open('health_news.csv', 'w', newline='', encoding='utf-8-sig')
csv_writer = csv.writer(csv_file)
csv_writer.writerow(['标题', '关键字', '时间'])

ctime = []
ckeyword = []

total_pages = 5
current_page = 1

while current_page <= total_pages:
    # 使用XPath定位新闻标题、关键字和时间元素
    titles = driver.find_elements(By.XPATH, "/html/body/div[4]/div[1]/div/div[2]/div[1]/div/div/h3/a[2]")
    keywords = driver.find_elements(By.XPATH, "/html/body/div[4]/div[1]/div/div[2]/div[1]/div/div/div[2]/div/a")
    times = driver.find_elements(By.XPATH, "/html/body/div[4]/div[1]/div/div[2]/div[1]/div/div/div[2]/time")

    for i in range(len(titles)):
        try:
            title = titles[i].text.strip()
            keyword = keywords[i].text.strip('#')
            timess = times[i].text.strip()
        except:
            pass

        # 输出标题、关键字和时间
        print(f"标题: {title}")
        print(f"关键字: {keyword}")
        print(f"时间: {timess}")

        # 写入CSV文件
        csv_writer.writerow([title, keyword, timess])

    # 自动翻页
    next_button = driver.find_element(By.XPATH, "/html/body/div[4]/div[1]/div/div[2]/div[2]/p/a[4]")
    next_button.click()
    time.sleep(2)  # 等待页面加载

    current_page += 1



# 关闭CSV文件
csv_file.close()

# 关闭浏览器
driver.quit()

爬取结果