import time import os import requests from io import BytesIO from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.common.by import By from selenium.webdriver.chrome.options import Options from webdriver_manager.chrome import ChromeDriverManager from bs4 import BeautifulSoup from reportlab.lib.pagesizes import letter from reportlab.lib import colors from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Image from reportlab.lib.styles import getSampleStyleSheet from reportlab.pdfbase.ttfonts import TTFont from reportlab.pdfbase import pdfmetrics from datetime import datetime from PIL import Image as PILImage import re from PyPDF2 import PdfReader, PdfWriter def download_image(url): """下载大于100KB的图片并返回临时文件路径，仅支持jpg、jpeg和png格式""" try: if not url.lower().endswith(('.jpg', '.jpeg', '.png')): return None headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36', 'Referer': 'https://tu.a7nz4.us', # 防止403 } response = requests.get(url, headers=headers) response.raise_for_status() # 确保请求成功 image = BytesIO(response.content) return image except requests.exceptions.RequestException as e: print(f"下载图片失败: {e}") return None def fetch_and_create_pdf(url): """根据给定URL抓取页面并生成PDF""" # 配置Selenium以无头模式运行 options = Options() options.headless = True options.add_argument('--disable-gpu') options.add_argument('--no-sandbox') # 使用webdriver-manager自动下载ChromeDriver driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options) # 获取目标页面 driver.get(url) time.sleep(5) # 处理“满18岁，请点此进入”按钮 try: enter_button = driver.find_element(By.XPATH, '//a[contains(text(), "满18岁，请点此进入")]') enter_button.click() print("点击了满18岁按钮") time.sleep(5) # 等待内容加载 except Exception as e: print("未找到满18岁按钮，跳过此步骤", e) # 使用BeautifulSoup解析页面 html = driver.page_source soup = BeautifulSoup(html, 'html.parser', from_encoding='utf-8') # 定位到帖子列表 posts = soup.find_all('tbody', {'id': lambda x: x and x.startswith('normalthread')}) # 获取今天的日期 today = datetime.now().strftime('%Y-%m-%d') # 注册中文字体 pdfmetrics.registerFont(TTFont('SimHei', 'fonts/simhei.ttf')) # 请确保字体文件路径正确 styles = getSampleStyleSheet() # 设置标题和正文样式 title_style = styles['Heading1'] title_style.fontName = 'SimHei' title_style.fontSize = 14 title_style.textColor = colors.red title_style.bold = True normal_style = styles['Normal'] normal_style.fontName = 'SimHei' content = [] # 过滤出当天的帖子 today_posts = [] for post in posts: post_time_span = post.find('span', {'class': 'xi1'}) if post_time_span: # 判断是否为当天帖子 today_posts.append(post) # 设置PDF pdf_filename = f"JAV-{today}-{len(today_posts)}.pdf" doc = SimpleDocTemplate(pdf_filename, pagesize=letter) # 遍历当天的帖子并提取信息 for post in today_posts: # 查找帖子标题 title = post.find('a', {'class': 's xst'}) if title: post_title = title.get_text() post_url = title.get('href') print(post_title) # 获取帖子页面 post_page_url = 'https://www.sehuatang.net/' + post_url driver.get(post_page_url) time.sleep(3) # 获取帖子页面内容 post_html = driver.page_source post_soup = BeautifulSoup(post_html, 'html.parser', from_encoding='utf-8') # 提取
下的文本和图片 content_div = post_soup.find('div', {'class': 't_fsz'}) if content_div: # 提取文本 post_text = content_div.get_text(strip=True) # 查找磁力链接 magnet_links = re.findall(r'magnet:\?[^ \u4e00-\u9fff]+', post_text) # 添加标题和来源URL content.append(Paragraph(f" {post_title}", title_style)) content.append(Spacer(1, 12)) # content.append(Paragraph(f"来源URL:
{post_page_url}
", normal_style)) # content.append(Spacer(1, 12)) # 解析并格式化 "介绍" 内容 # intro_content = [] # intro_lines = post_text.split("【") # 以【分割字段 # for line in intro_lines: # if line.strip(): # line = "【" + line if not line.startswith("【") else line # if "】：" in line: # key, value = line.split("】：", 1) # intro_content.append(Paragraph(f"{key}】：
{value}
", normal_style)) # intro_content.append(Spacer(1, 6)) # 字段间距 # # # 添加格式化的介绍部分 # content.append(Paragraph("介绍:
", normal_style)) # content.extend(intro_content) # content.append(Spacer(1, 12)) # 添加磁力链接 if magnet_links: for magnet_link in magnet_links: content.append(Paragraph(f"

{magnet_link}

", normal_style)) content.append(Spacer(1, 12)) # 添加图片 image_links = [] images = content_div.find_all('img') for img in images: if img.get('zoomfile') and 'http' in img.get('zoomfile'): image_links.append(img.get('zoomfile')) print(image_links) if image_links: for img_link in image_links: image = download_image(img_link) if image: img = PILImage.open(image) img_width, img_height = img.size image_width = 500 # 固定宽度 image_height = int((img_height / img_width) * image_width) img_stream = BytesIO(image.getvalue()) content.append(Image(img_stream, width=image_width, height=image_height)) content.append(Spacer(1, 12)) content.append(Spacer(1, 12)) # 帖子间距 # 生成PDF doc.build(content) # 获取PDF绝对路径 absolute_pdf_path = os.path.abspath(pdf_filename) print(f"PDF saved as {absolute_pdf_path}") # 加密PDF add_pdf_encryption(absolute_pdf_path) # 关闭浏览器 driver.quit() return absolute_pdf_path def add_pdf_encryption(pdf_file, password="4000"): """使用PyPDF2为PDF添加加密保护""" pdf_writer = PdfWriter() pdf_reader = PdfReader(pdf_file) # 将所有页面添加到PDF写入器 for page_num in range(len(pdf_reader.pages)): pdf_writer.add_page(pdf_reader.pages[page_num]) # 添加密码 pdf_writer.encrypt(password) # 保存加密后的PDF with open(pdf_file, "wb") as output_pdf: pdf_writer.write(output_pdf) print(f"PDF加密成功，密码为: {password}") def pdf_file_path(): url = 'https://www.sehuatang.net/forum.php?mod=forumdisplay&fid=103&filter=typeid&typeid=481' pdf_path = fetch_and_create_pdf(url) print(f"返回的PDF文件路径：{pdf_path}") return pdf_path if __name__ == "__main__": pdf_file_path()