Python-查询-循环列表-跳转-下载文件

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from urllib.parse import urljoin
import requests
from bs4 import BeautifulSoup
import time

service = Service('C:\chromedriver-win64\chromedriver.exe')
driver = webdriver.Chrome(service=service)
# 指定ChromeDriver的路径
#driver_path = 'path/to/chromedriver.exe'

# 创建一个Service对象
#service = Service(executable_path=driver_path)

# 使用Service对象初始化Chrome WebDriver
#driver = webdriver.Chrome(service=service)

# 接下来你可以使用driver对象来操作浏览器
driver.get('https://xxx/xxxx/xxxx/xxxx')
time.sleep(50)

# 定位搜索框并输入搜索关键词
#search_box = driver.find_element(By.ID, "xxxx")  # 请根据实际页面元素ID进行修改
search_box = driver.find_element(By.ID, "xxxxxx")
search_box.send_keys("xxxxx")
search_box.send_keys(Keys.RETURN)

time.sleep(30)

# 假设有一个按钮用于提交查询，这里使用XPath示例，实际使用时需根据网页结构调整
submit_icon = driver.find_element(By.XPATH, "//div[@class='xxxxxx']")
submit_icon.click()

time.sleep(30)

'''
# 查找包含 onclick 属性的div元素
div_tag = driver.find_element(By.CSS_SELECTOR, 'div.xxxx.clickable')
base_url = "https://xxxx.xxxx.xxx.xx"
# 获取 onclick 属性中的相对路径
onclick_attr = div_tag.get_attribute('xxxx')
relative_path = onclick_attr.split("'")[1]
absolute_url = urljoin(base_url, relative_path)
#relative_paths = []
print("Relative Path:", relative_path)
print("absolute_url:", absolute_url)
driver.get(absolute_url)
'''

# 获取结果列表中每个元素的onclick属性的相对路径
results = driver.find_elements(By.CSS_SELECTOR, 'div.xxxx.clickable')
relative_paths = []
for result in results:
    onclick_attr = result.get_attribute('xxxxxx')
    relative_path = onclick_attr.split("'")[1]
    relative_paths.append(relative_path)
    print(relative_path)

# 拼接完整URL并循环点击打开页面
base_url = 'https://xxxxx.xxxx.xxxx.xx/'
for relative_path in relative_paths:
    full_url = urljoin(base_url, relative_path)
    print(full_url)
    driver.get(full_url)
    time.sleep(30)
    result_link = driver.find_element(By.CLASS_NAME, "xxxxxx")
    result_link.click()

time.sleep(30)


#result_link = driver.find_element(By.CLASS_NAME, "xxxxxx")
#result_link.click()

# 假设文件下载链接在一个class为"download-link"的元素内
# 这里的选择器需要根据目标网页的实际结构进行调整
#download_links = driver.find_elements(By.CLASS_NAME, "xxxxx clickable")

# 循环遍历每个下载链接并点击
#for link in download_links:
    #link.click()
    # 等待文件下载完成，这里简单地使用time.sleep，实际应用中可能需要更复杂的逻辑
    #time.sleep(5)  # 等待5秒，这取决于你的网络速度和文件大小
#result_link = driver.find_element(By.XPATH, "/html/body/div[4]/div[1]/div/div[1]/div[1]/div[2]")
#result_link.click()

time.sleep(30)

#base_url = "https://xxxx"


#result_link = driver.find_element(By.CLASS_NAME, "xxxxx")
#result_link.click()

#time.sleep(30)
# 记得在结束时关闭浏览器
driver.quit()