init

parsers/douyin.py

@@ -0,0 +1,89 @@
+from parsers.base import BaseParser
+from typing import Dict
+from urllib.parse import urlencode
+
+class DouyinParser(BaseParser):
+    """抖音解析器"""
+
+    def parse(self, video_url: str) -> Dict:
+        """解析抖音视频"""
+        try:
+            # 步骤1: 提取视频ID
+            aweme_id = self._get_aweme_id(video_url)
+
+            # 步骤2: 获取视频详细信息
+            video_info = self._fetch_video_info(aweme_id)
+
+            # 步骤3: 提取并标准化数据
+            return self._extract_data(video_info)
+        except Exception as e:
+            raise Exception(f"抖音解析失败: {str(e)}")
+
+    def _get_aweme_id(self, video_url: str) -> str:
+        """提取视频ID"""
+        # 手动构建URL，避免双重编码
+        url = f"{self.api_url}/api/douyin/web/get_aweme_id?{urlencode({'url': video_url})}"
+
+        response = self._make_request(url)
+        data = response.json()
+
+        if data.get("code") != 200:
+            raise Exception(f"获取视频ID失败: {data.get('msg', '未知错误')}")
+
+        return data.get("data")
+
+    def _fetch_video_info(self, aweme_id: str) -> Dict:
+        """获取视频详细信息"""
+        # 手动构建URL，避免双重编码
+        url = f"{self.api_url}/api/douyin/web/fetch_one_video?{urlencode({'aweme_id': aweme_id})}"
+
+        response = self._make_request(url)
+        data = response.json()
+
+        if data.get("code") != 200:
+            raise Exception("获取视频信息失败")
+
+        return data.get("data", {}).get("aweme_detail", {})
+
+    def _extract_data(self, video_info: Dict) -> Dict:
+        """提取并标准化数据"""
+        try:
+            # 提取封面
+            cover = video_info.get("video", {}).get("cover_original_scale", {}).get("url_list", [""])[0]
+
+            # 提取视频URL
+            video_url = video_info.get("video", {}).get("play_addr", {}).get("url_list", [""])[0]
+
+            # 提取标题（描述）
+            title = video_info.get("desc", "")
+
+            # 提取作者信息作为简介
+            author = video_info.get("author", {})
+            author_name = author.get("nickname", "")
+            author_signature = author.get("signature", "")
+            description = f"作者: {author_name}"
+            if author_signature:
+                description += f" | {author_signature}"
+
+            return self._normalize_response(cover, video_url, title, description)
+        except Exception as e:
+            raise Exception(f"数据提取失败: {str(e)}")
+
+
+class DouyinDownloadParser(BaseParser):
+    """抖音下载解析器（直接下载）"""
+
+    def parse(self, video_url: str) -> Dict:
+        """解析抖音视频（下载方式）"""
+        try:
+            download_url = f"{self.api_url}/api/download"
+
+            # 手动构建URL，避免双重编码
+            return self._normalize_response(
+                cover="",
+                video_url=f"{download_url}?{urlencode({'url': video_url})}",
+                title="抖音视频",
+                description="通过下载接口获取"
+            )
+        except Exception as e:
+            raise Exception(f"抖音下载解析失败: {str(e)}")