76 lines
2.8 KiB
Python
76 lines
2.8 KiB
Python
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
|
||
from bs4 import BeautifulSoup
|
||
import time
|
||
|
||
# 初始化 WebDriver
|
||
options = webdriver.ChromeOptions()
|
||
options.add_argument('--headless') # 无头模式，不打开浏览器界面
|
||
driver = webdriver.Chrome(options=options)
|
||
|
||
try:
|
||
# 打开金十数据网站
|
||
driver.get("https://www.jin10.com/")
|
||
|
||
# 等待网页加载并找到目标元素
|
||
target_xpath = '/html/body/div[1]/div[2]/div[2]/div/main/div[2]/div[2]/div[2]/div[2]/div[2]/div[4]/span[2]/div[1]/div[3]/div/div[2]/div[3]'
|
||
target_element = WebDriverWait(driver, 20).until(
|
||
EC.presence_of_element_located((By.XPATH, target_xpath))
|
||
)
|
||
|
||
# 使用 JavaScript 修改元素的 class
|
||
script = '''
|
||
var element = document.evaluate(arguments[0], document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
|
||
element.className = "hot-filter_item is-active";
|
||
'''
|
||
driver.execute_script(script, target_xpath)
|
||
|
||
# 立即更新内容，假设更新内容的位置是已知的
|
||
update_xpath = '/html/body/div[1]/div[2]/div[2]/div/main/div[2]/div[2]/div[3]'
|
||
update_element = WebDriverWait(driver, 20).until(
|
||
EC.presence_of_element_located((By.XPATH, update_xpath))
|
||
)
|
||
|
||
# 触发页面更新，这里假设更新内容是通过某种操作，比如点击按钮或其他方式
|
||
# 请根据实际情况调整这里的操作
|
||
driver.execute_script('arguments[0].scrollIntoView(true);', update_element)
|
||
time.sleep(5) # 等待页面内容更新
|
||
|
||
# 获取页面内容
|
||
page_source = driver.page_source
|
||
|
||
# 使用 BeautifulSoup 解析 HTML
|
||
soup = BeautifulSoup(page_source, 'lxml')
|
||
|
||
# 提取 class 为 'jin-flash-item-container is-normal' 的 div 标签
|
||
items = soup.find_all('div', class_='jin-flash-item-container is-normal')
|
||
|
||
# 只爬取前5条信息
|
||
# 初始化匹配计数器
|
||
matched_count = 0
|
||
|
||
# 只爬取包含关键词的信息
|
||
for index, item in enumerate(items[:40], start=1):
|
||
text_content = item.get_text(strip=True)
|
||
# print(text_content)
|
||
|
||
if '默认火热沸爆' not in text_content:
|
||
continue
|
||
|
||
matched_count += 1
|
||
# print(items[1])
|
||
parts = text_content.split('默认火热沸爆', 1)#默认火热沸爆
|
||
if len(parts) > 1:
|
||
print(f"匹配信息 {matched_count}:")
|
||
if parts[1].strip():
|
||
modified_text = parts[1].strip()[0] + "：" + parts[1].strip()[1:]
|
||
print(modified_text)
|
||
else:
|
||
print("")
|
||
print(f"\n共找到 {matched_count} 条匹配'默认火热沸爆'的信息")
|
||
|
||
finally:
|
||
# 关闭 WebDriver
|
||
driver.quit() |