爬虫，开发人员工具要熟练使用
爬文库可预览页面。图片链接有规律。import os
from PIL import Image
from fpdf import FPDF
import shutil
from datetime import datetime
from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep
import requests
def download_image_with_requests(image_url, save_path):
"""
使用requests库下载图片并保存到指定路径
:param image_url: 图片的URL
:param save_path: 保存路径（包括文件名）
"""
try:
response = requests.get(image_url, stream=True)
response.raise_for_status()# 如果请求失败，将抛出HTTPError异常
with open(save_path, 'wb') as file:
for chunk in response.iter_content(chunk_size=8192):
file.write(chunk)
print(f"Image downloaded successfully to {save_path}")
except requests.exceptions.HTTPError as errh:
print(f"Http Error: {errh}")
except requests.exceptions.ConnectionError as errc:
print(f"Error Connecting: {errc}")
except requests.exceptions.Timeout as errt:
print(f"Timeout Error: {errt}")
except requests.exceptions.RequestException as err:
print(f"OOps: Something Else: {err}")
def merge_jpg_to_pdf_and_delete_folder(folder_path):
# 创建一个FPDF对象
pdf = FPDF()
# 遍历文件夹中的所有文件
for filename in os.listdir(folder_path):
if filename.endswith(".jpg") or filename.endswith(".jpeg"):
# 打开图片并获取其尺寸
image_path = os.path.join(folder_path, filename)
with Image.open(image_path) as img:
# 将图片添加到PDF中，这里假设图片尺寸适应PDF页面大小
pdf.add_page()
pdf.image(image_path, 0, 0, 210)# 假设PDF页面大小为A4，即210mm宽
# 获取当前日期和时间
now = datetime.now()
# 格式化日期和时间，例如：2023-04-01_15-30-45.jpg
timestamp = now.strftime("%Y%m%d%H%M%S")
# 创建文件名，假设文件扩展名为.jpg
filename = f"{timestamp}.pdf"
# 使用os.path.dirname来获取父目录
folder_path1 = os.path.dirname(folder_path)
# 拼接文件夹路径和文件名
pdf_path = os.path.join(folder_path1, filename)
# 保存PDF文件，这里假设PDF文件名为merged.pdf，保存在当前目录下
pdf.output(pdf_path, "F")
# 删除文件夹及其内容
shutil.rmtree(folder_path)
print(f"PDF file {pdf_path} created and folder {folder_path} deleted.")
folder_path = 'D:/图片'# 替换为你想要创建的文件夹路径
# 使用makedirs创建文件夹，如果文件夹已存在且exist_ok=True，则不会抛出异常
os.makedirs(folder_path, exist_ok=True)
driver = webdriver.Edge()
driver.maximize_window()
print("网址格式示例：https://www.renrendoc.com/paper/239626450.html")
url = input("请输入类似文章网址：")
driver.get(url)
image = driver.find_element(By.XPATH, '//*[@id="page"]/div/img')
driver.execute_script("arguments.scrollIntoView();", image)
sleep(1)
lk = image.get_attribute("src")
ims =
print(ims)
n = int(driver.find_element(By.CLASS_NAME,"total").text)
if n > 5:
n = 6
for i in range(2, n):
ims.append(lk[:-5]+str(i)+'.gif')
print(ims)
for im in ims:
save_path = os.path.join("d:/图片", str(ims.index(im)+1) + '.jpg')
download_image_with_requests(im, save_path)
# 使用函数，传入包含JPG图片的文件夹路径
merge_jpg_to_pdf_and_delete_folder("d:/图片")
zjg121 发表于 2024-3-27 09:17
使用selenium，需要安装和edge浏览器版本一致的驱动Microsoft Edge WebDriver。
我按提示输入了一个 搜狐网址，然后打开了网页，原来是提示安全问题，但有许多提示，不知道啥意思：
%Run 25.py
Exception trying to discover chromedriver version: error sending request for url (https://chromedriver.storage.googleapis.com/LATEST_RELEASE_109): error trying to connect: 远程主机强迫关闭了一个现有的连接。 (os error 10054)
网址格式示例：https://www.renrendoc.com/paper/239626450.html
请输入类似文章网址：https://www.sohu.com/
Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\python学习\25.py", line 80, in <module>
image = driver.find_element(By.XPATH, '//*[@id="page"]/div/img')
File "C:\Users\Administrator\AppData\Local\Programs\Thonny\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 739, in find_element
return self.execute(Command.FIND_ELEMENT, {"using": by, "value": value})["value"]
File "C:\Users\Administrator\AppData\Local\Programs\Thonny\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 345, in execute
self.error_handler.check_response(response)
File "C:\Users\Administrator\AppData\Local\Programs\Thonny\lib\site-packages\selenium\webdriver\remote\errorhandler.py", line 229, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.NoSuchElementException: Message: no such element: Unable to locate element: {"method":"xpath","selector":"//*[@id="page"]/div/img"}
(Session info: chrome=109.0.5414.120); For documentation on this error, please visit: https://www.selenium.dev/documentation/webdriver/troubleshooting/errors#no-such-element-exception
Stacktrace:
Backtrace:
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
(No symbol)
GetHandleVerifier
GetHandleVerifier
GetHandleVerifier
GetHandleVerifier
(No symbol)
(No symbol)
(No symbol)
(No symbol)
BaseThreadInitThunk
RtlInitializeExceptionChain
RtlInitializeExceptionChain
>>>
kolt1911 发表于 2024-3-27 09:23
webdriver.edge()修改成chrome可以吗
改成：driver = webdriver.Chrome()
Exception trying to discover chromedriver version: error sending request for url (https://chromedriver.storage.googleapis.com/LATEST_RELEASE_109): error trying to connect: 远程主机强迫关闭了一个现有的连接。 (os error 10054) 想入门爬虫，但是不知道哪里开始，还是说啃书就可以？？？ 我是新手，也想学爬虫，同楼上的问题 爬虫成熟工具多，自学意义不大 我是新手，也想学爬虫 学习了一下 好用，我也去试试。 kingisme945 发表于 2024-3-27 00:32
爬虫成熟工具多，自学意义不大
不成熟的呢？ 我是新手,学习！ ltgb 发表于 2024-3-27 06:48
不成熟的呢？
不成熟用python