Initial commit: LookingWeb project

2026-08-30 09:15:34 +08:00
commit f8e8fd38b4
5 changed files with 276 additions and 0 deletions
@@ -0,0 +1,96 @@
+import time
+
+import requests
+from loguru import logger
+from bs4 import BeautifulSoup
+from dataService.dto.SeedInfo import SeedInfo
+from dataService import MySqlService as mysql
+from ariaDownloaderService import AriaDownloader as ariaDownloader
+
+"""
+获取页面信息
+"""
+def get_page(url):
+    logger.debug("开始获取页面信息：{}", url)
+    try:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.content, 'html.parser')
+        logger.debug("页面信息获取成功。URL: {}", url)
+        return soup
+    except Exception as e:
+        logger.error("获取页面信息失败。URL: {}, 错误: {}", url, str(e))
+        return None
+
+
+"""
+用于获取目标元素上的详情页url
+"""
+def get_target_element_list(page_content):
+    logger.debug("开始提取可下载内容的链接")
+    downloadable_url_list = []
+    try:
+        for element in page_content.find_all("div", {"class": "card-body"}):
+            if "可下" in element.find("div", {"class": "video-list-item-tag-wrapper"}).text:
+                url = element.find("a")["href"]
+                downloadable_url_list.append(url)
+                logger.debug("发现可下载链接: {}", url)
+        logger.debug("链接提取完成。共发现 {} 个链接。", len(downloadable_url_list))
+        return downloadable_url_list
+    except Exception as e:
+        logger.error("提取链接时出现错误: {}", str(e))
+        return []
+
+
+def get_seed_from_element_detail(element_detail):
+    logger.debug("开始解析页面中的种子信息")
+    seedInfoList = []
+    time.sleep(2)
+    try:
+        from_url = element_detail.find("link")["href"]
+        title = element_detail.find("meta", {"name": "description"})["content"]
+        for e in element_detail.find("tbody").find_all("a", class_="magnet-name text-truncate d-block small"):
+            seedInfo = SeedInfo(title, e["href"], "1", url=from_url)
+            seedInfoList.append(seedInfo)
+            logger.debug("解析到种子信息: 标题：{}，链接：{}", title, e["href"])
+        logger.debug("页面种子信息解析完成。共 {} 个种子。", len(seedInfoList))
+        return seedInfoList
+    except Exception as e:
+        logger.error("解析种子信息时出现错误: {}", str(e))
+        return []
+
+
+def main():
+    # 1-18
+    for page in range(5):
+        url = f"https://freejavbt.com/censored/filter?c=212&page={page+1}"
+        logger.info("程序启动。开始处理 URL: {}", url)
+        new_seed = []
+        # 获取页面信息
+        page = get_page(url)
+        if page is not None:
+            # 获取页面中的目标元素所包含的详情页信息(url列表)
+            targetElementList = get_target_element_list(page)
+            for targetElement in targetElementList:
+                element_detail = get_page(targetElement)
+                if element_detail is not None:
+                    seed_list = get_seed_from_element_detail(element_detail)
+                    # 将新发现的种子存储进new_seed列表
+                    for seed in seed_list:
+                        if not mysql.seed_is_exist(seed):
+                            new_seed.append(seed)
+                            logger.debug("新增种子到下载列表: {}", seed.name)
+
+            # 推送new_seed进入aria2进行种子下载
+            for seed in new_seed:
+                logger.info("开始下载种子: {}", seed.name)
+                status = ariaDownloader.download_by_seed(seed)  # 返回值取值1，0，-1
+                seed.haveDownload = status
+                seed.seave_to_dataBase()
+                logger.info("种子下载完成。标题: {}, 状态: {}", seed.name, "成功" if status == "1" else "失败")
+        else:
+            logger.error("无法获取网页内容。URL: {}", url)
+
+        logger.info("程序处理完成。")
+
+if __name__ == "__main__":
+    main()