利用Python与Selenium在现有浏览器会话中提取文本：策略与实践

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time

def automate_login_and_extract(url, username, password, target_element_selector):
    driver = webdriver.Chrome() # 或Firefox, Edge等
    driver.get(url)

    try:
        # 等待用户名输入框出现
        username_field = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "username")) # 根据实际情况修改ID或XPath
        )
        username_field.send_keys(username)

        # 等待密码输入框出现
        password_field = driver.find_element(By.ID, "password") # 根据实际情况修改ID或XPath
        password_field.send_keys(password)

        # 定位并点击登录按钮
        login_button = driver.find_element(By.ID, "loginButton") # 根据实际情况修改ID或XPath
        login_button.click()

        # 登录后等待页面加载，可以根据URL变化或某个元素出现来判断
        WebDriverWait(driver, 15).until(
            EC.url_contains("dashboard") # 假设登录后跳转到包含"dashboard"的URL
        )
        print("登录成功！")

        # 提取目标文本
        target_element = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.CSS_SELECTOR, target_element_selector))
        )
        text_content = target_element.text
        print(f"提取到的文本: {text_content}")
        return text_content

    except Exception as e:
        print(f"自动化登录或文本提取失败: {e}")
        return None
    finally:
        driver.quit()

# 示例调用
# login_url = "https://example.com/login"
# my_username = "your_username"
# my_password = "your_password"
# element_to_extract_selector = "#some_id .some_class" # CSS选择器
#
# extracted_text = automate_login_and_extract(login_url, my_username, my_password, element_to_extract_selector)

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
import os

def reuse_profile_and_extract(url, profile_path, target_element_selector):
    chrome_options = Options()
    # 注意：profile_path 应该是 User Data 的父目录，而不是 Default 目录
    # 例如，如果你的配置文件路径是 C:\Users\YourUser\AppData\Local\Google\Chrome\User Data\Default
    # 那么你应该传入 C:\Users\YourUser\AppData\Local\Google\Chrome\User Data
    chrome_options.add_argument(f"user-data-dir={profile_path}")
    # 可以选择指定使用哪个profile，例如 Default 或 Profile 1
    # chrome_options.add_argument("profile-directory=Default") 

    driver = webdriver.Chrome(options=chrome_options)
    driver.get(url)

    try:
        # 等待页面加载，或者直接检查目标元素
        WebDriverWait(driver, 15).until(
            EC.presence_of_element_located((By.CSS_SELECTOR, target_element_selector))
        )
        print("成功加载已登录会话并访问页面。")

        # 提取目标文本
        target_element = driver.find_element(By.CSS_SELECTOR, target_element_selector)
        text_content = target_element.text
        print(f"提取到的文本: {text_content}")
        return text_content

    except Exception as e:
        print(f"复用配置文件或文本提取失败: {e}")
        return None
    finally:
        driver.quit()

# 示例调用
# 请根据你的实际情况修改 profile_path 和 target_url
# Windows 示例：
# chrome_user_data_path = r"C:\Users\YourUser\AppData\Local\Google\Chrome\User Data"
# macOS 示例：
# chrome_user_data_path = os.path.expanduser("~/Library/Application Support/Google/Chrome")
# Linux 示例：
# chrome_user_data_path = os.path.expanduser("~/.config/google-chrome")

# target_url = "https://stackoverflow.com/" # 假设Stack Overflow已登录
# element_to_extract_selector = "#question-header .s-link" # 提取问题标题

# extracted_text = reuse_profile_and_extract(target_url, chrome_user_data_path, element_to_extract_selector)

from selenium import webdriver
from selenium.webdriver.firefox.options import Options

# 假设你的Firefox配置文件路径是 /path/to/your/firefox/profile
# 例如：/Users/YourUser/Library/Application Support/Firefox/Profiles/abcdefgh.default-release
firefox_profile_path = "/path/to/your/firefox/profile" 

firefox_options = Options()
firefox_options.add_argument(f"-profile {firefox_profile_path}")

driver = webdriver.Firefox(options=firefox_options)
driver.get("https://example.com")
# ... 后续操作
driver.quit()