使用Python+Selenium爬取时生成空白PDF的问题求助

在网页https://jamabandi.nic.in/land%20records/NakalRecord上，通过Selenium选择各下拉框首个选项后触发生成PDF操作，网页上明明显示有表格内容，但手动和自动化打印出的PDF始终为空白。相关代码如下：

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

service = Service()
options = webdriver.ChromeOptions()
# Set up preferences for printing to PDF
settings = {
    "recentDestinations": [{"id": "Save as PDF", "origin": "local", "account": ""}],
    "selectedDestinationId": "Save as PDF",
    "version": 2
}
prefs = {
    'printing.print_preview_sticky_settings.appState': json.dumps(settings),
    'printing.print_to_file': True,
    'printing.print_to_file.path': '/Users/jatin/Downloads/output.pdf'  # Specify the desired output path
}
chrome_options.add_experimental_option('prefs', prefs)

import urllib.request
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
# Set up Chrome options
chrome_options = Options()
# chrome_options.add_argument('--headless')  # Optional: Run Chrome in headless mode
chrome_options.add_argument('--kiosk-printing')
try:
    service = Service(ChromeDriverManager().install())
except ValueError:
    latest_chromedriver_version_url = "https://chromedriver.storage.googleapis.com/LATEST_RELEASE"
    latest_chromedriver_version = urllib.request.urlopen(latest_chromedriver_version_url).read().decode('utf-8')
    service = Service(ChromeDriverManager(version=latest_chromedriver_version).install())

    
options = Options()
url='https://jamabandi.nic.in/land%20records/NakalRecord'
# options.add_argument('--headless') #optional.
driver = webdriver.Chrome(service=service, options=options)
driver.get(url)


dropdown_district = Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddldname"]'))
dropdown_district.select_by_index(1)
# Select the tehsil dropdown element and choose the first option,we will loop here for multiple anchals
drop_down_tehsil = Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddltname"]'))
drop_down_tehsil.select_by_index(1)
drop_down_vill = Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlvname"]'))
drop_down_vill.select_by_index(1)
drop_down_year = Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlPeriod"]'))
drop_down_year.select_by_index(1)
owner_names=Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ListBox1"]'))
dropdown_locator = (By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ListBox1"]')
drop_down_owner = Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlOwner"]'))
drop_down_owner.select_by_index(1)
owner_names =Select(driver.find_element(By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ListBox1"]'))
owner_names.select_by_index(2)
page_source = BeautifulSoup(driver.page_source, 'html.parser')
table = page_source.find_all('table')
div_col_lg_12 = page_source.find('div', class_='col-lg-12')

# Find links within the selected div
links_within_div = div_col_lg_12.find_all('td')
links_within_div
# Perform actions on the links or retrieve their attributes
for link in links_within_div:
    k=link.find_all('a')
    if len(k)>0:
        new_link=(k[0]['href'])
        
javascript_code = str(new_link)

# Execute the JavaScript code
driver.execute_script(javascript_code)

window_handles=driver.window_handles
driver.switch_to.window(window_handles[-1])

# Open the print dialog using JavaScript
driver.execute_script('window.print();')

问题分析及解决办法 #

核心问题点 #

1. 代码中重复定义options和chrome_options变量，导致打印偏好配置未被正确应用
2. 未等待新窗口的PDF内容完全渲染就触发打印
3. 通过执行href脚本打开新窗口的方式稳定性不足
4. 未启用打印背景图形的配置，可能导致部分内容无法被捕获

修正后的代码 #

import json
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select, WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from webdriver_manager.chrome import ChromeDriverManager
import urllib.request

# 统一Chrome配置，避免变量冲突
chrome_options = Options()
# 配置PDF打印参数，启用背景图形确保内容完整
print_settings = {
    "recentDestinations": [{"id": "Save as PDF", "origin": "local", "account": ""}],
    "selectedDestinationId": "Save as PDF",
    "version": 2,
    "isCssBackgroundEnabled": True
}
prefs = {
    'printing.print_preview_sticky_settings.appState': json.dumps(print_settings),
    'printing.print_to_file': True,
    'printing.print_to_file.path': '/Users/jatin/Downloads/output.pdf'
}
chrome_options.add_experimental_option('prefs', prefs)
chrome_options.add_argument('--kiosk-printing')
# chrome_options.add_argument('--headless=new')  # 如需无头模式，建议使用新版无头参数

# 初始化Chrome驱动
try:
    service = Service(ChromeDriverManager().install())
except ValueError:
    latest_version = urllib.request.urlopen("https://chromedriver.storage.googleapis.com/LATEST_RELEASE").read().decode('utf-8')
    service = Service(ChromeDriverManager(version=latest_version).install())

driver = webdriver.Chrome(service=service, options=chrome_options)
driver.get('https://jamabandi.nic.in/land%20records/NakalRecord')

# 显式等待所有元素可交互，避免页面未加载完成就操作
wait = WebDriverWait(driver, 10)

# 依次选择下拉框选项
district_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddldname"]'))))
district_dropdown.select_by_index(1)

tehsil_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddltname"]'))))
tehsil_dropdown.select_by_index(1)

vill_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlvname"]'))))
vill_dropdown.select_by_index(1)

year_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlPeriod"]'))))
year_dropdown.select_by_index(1)

owner_type_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ddlOwner"]'))))
owner_type_dropdown.select_by_index(1)

owner_name_dropdown = Select(wait.until(EC.element_to_be_clickable((By.XPATH, '//*[@id="ctl00_ContentPlaceHolder1_ListBox1"]'))))
owner_name_dropdown.select_by_index(2)

# 等待Nakal链接加载完成，直接点击而非执行脚本
nakal_link = wait.until(EC.element_to_be_clickable((By.XPATH, '//div[@class="col-lg-12"]//td//a')))
original_window = driver.current_window_handle
nakal_link.click()

# 等待新窗口打开并切换
wait.until(EC.number_of_windows_to_be(2))
for window_handle in driver.window_handles:
    if window_handle != original_window:
        driver.switch_to.window(window_handle)
        break

# 等待PDF页面完全渲染，增加额外等待确保内容加载完成
wait.until(EC.presence_of_element_located((By.TAG_NAME, 'body')))
driver.implicitly_wait(5)

# 触发打印
driver.execute_script('window.print();')

# 结束操作后关闭驱动
# driver.quit()

关键优化说明 #

• 合并了重复的Chrome配置变量，确保打印偏好生效
• 全程使用显式等待，避免因页面加载延迟导致的元素未就绪问题
• 直接点击链接元素替代执行href脚本，提升操作稳定性
• 启用了isCssBackgroundEnabled配置，确保网页样式和背景内容能被正确打印
• 增加了PDF页面渲染后的等待时间，避免内容未加载完成就触发打印

内容的提问来源于stack exchange，提问作者jatin rajani