下载图片代码：https://www.lzslib.org.cn/nd.jsp?id=（651，659）
[Python] 纯文本查看 复制代码 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 requests
import os
from time import sleep
# 初始化WebDriver
driver = webdriver.Edge() # 请替换为您的chromedriver路径
sh = [i for i in range(651, 660)]
for s in sh:
ls = f'https://www.lzslib.org.cn/nd.jsp?id={s}'
try:
# 打开网页
driver.get(ls) # 替换为您的目标网页URL
sleep(3)
bt = driver.title.split('-')[0]
# 找到网页元素并提取属性值（这里假设是一个链接）
tps = driver.find_elements(By.TAG_NAME, 'img') # 替换为合适的CSS选择器或其他定位器
print(len(tps))
for tp in tps:
tp_url = tp.get_attribute('src')
# 下载PDF
response = requests.get(tp_url, stream=True)
with open(f"d:/a/img/{bt.replace('一','1').replace('二','2').replace('三','3').replace('四','4')}_{str(tps.index(tp)).zfill(3)}.jpg", 'wb') as f:
for chunk in response.iter_content(chunk_size=8192):
if chunk:
f.write(chunk)
print("PDF downloaded successfully.")
finally:
# 关闭WebDriver
pass
driver.quit() | 
发表于 2024-4-18 08:07
|
发表于 2024-4-18 08:39
