diff --git a/README.md b/README.md index ee8aa9f..8e12c0b 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ **基于 Python 的多平台媒体原生本地解析系统** -[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![Python Version](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/) [![Support](https://img.shields.io/badge/support-28+%20Platforms-brightgreen.svg)](#💾-支持的平台矩阵) +[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![Python Version](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/) [![Support](https://img.shields.io/badge/support-29+%20Platforms-brightgreen.svg)](#💾-支持的平台矩阵)

解析逻辑 • @@ -49,6 +49,7 @@ | **即梦 AI** | ✓ | ✓ | ✓ | ✓ | | | | | **可灵 AI** | ✓ | ✓ | ✓ | ✓ | | | | | **通义千问** | ✓ | ✓ | ✓ | ✓ | ✓ | | | +| **闲鱼** | | ✓ | ✓ | | ✓ | | | | **Soul** | ✓ | ✓ | ✓ | ✓ | ✓ | | | | **汽水音乐** | ✓ | ✓ | ✓ | ✓ | | ✓ | | | **腾讯频道** | ✓ | ✓ | ✓ | ✓ | | | | diff --git a/configs/business_config.json b/configs/business_config.json index 6736087..2cf46bb 100755 --- a/configs/business_config.json +++ b/configs/business_config.json @@ -52,7 +52,12 @@ "channels.weixin.qq.com": "微信视频号", "activity.qianwen.com": "通义千问", "qianwen.aliyun.com": "通义千问", - "tongyi.aliyun.com": "通义千问" + "tongyi.aliyun.com": "通义千问", + "e.tb.cn": "闲鱼", + "m.tb.cn": "闲鱼", + "tb.cn": "闲鱼", + "h5.m.goofish.com": "闲鱼", + "2.taobao.com": "闲鱼" }, "USER_AGENT_PC": [ "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36", diff --git a/src/parser_factory.py b/src/parser_factory.py index cdf6f93..70d0e2e 100644 --- a/src/parser_factory.py +++ b/src/parser_factory.py @@ -26,6 +26,7 @@ from src.parsers.qsmusic_parser import QSMusicParser from src.parsers.tencent_channel_parser import TencentChannelParser from src.parsers.jianying_parser import JianyingParser from src.parsers.qianwen_parser import QianwenParser +from src.parsers.xianyu_parser import XianyuParser class ParserFactory: platform_to_parser = { @@ -57,6 +58,7 @@ class ParserFactory: "腾讯频道": TencentChannelParser, "剪映": JianyingParser, "通义千问": QianwenParser, + "闲鱼": XianyuParser, } @staticmethod diff --git a/src/parsers/xianyu_parser.py b/src/parsers/xianyu_parser.py new file mode 100644 index 0000000..96b2a28 --- /dev/null +++ b/src/parsers/xianyu_parser.py @@ -0,0 +1,76 @@ +import re +from urllib.parse import parse_qs, urlparse + +from configs.general_constants import USER_AGENT_M +from configs.logging_config import get_logger +from src.parsers.base_parser import BaseParser + +logger = get_logger(__name__) + + +class XianyuParser(BaseParser): + """闲鱼/淘宝短链解析器,提取商品 ID、标价与真实目标链接。""" + + def __init__(self, real_url): + super().__init__(real_url) + self.headers = { + "User-Agent": USER_AGENT_M[0], + "Referer": "https://e.tb.cn/", + } + self.item_id = None + self.price = None + self.target_url = None + self.title = None + self.cover_url = None + self.video_url = None + self.image_list = [] + self.author = None + self._parse() + + def _parse(self): + if not self.real_url: + return + try: + resp = self.session.get(self.real_url, headers=self.headers, timeout=10) + resp.raise_for_status() + + match = re.search(r"var\s+url\s*=\s*'([^']+)'", resp.text) + if match: + self.target_url = match.group(1) + parsed = urlparse(self.target_url) + params = parse_qs(parsed.query) + self.item_id = (params.get("id") or [None])[0] + self.price = (params.get("price") or [None])[0] + + if not self.item_id: + parsed_real = urlparse(self.real_url) + params_real = parse_qs(parsed_real.query) + self.item_id = (params_real.get("id") or [None])[0] + + if self.target_url: + self.image_list = [self.target_url] + self.cover_url = self.target_url + + if self.item_id: + if self.price: + self.title = f"闲鱼商品 (商品ID: {self.item_id}, 标价: ¥{self.price})" + else: + self.title = f"闲鱼商品 (商品ID: {self.item_id})" + + except Exception as exc: + logger.warning("Failed to parse Xianyu share URL: %s", exc) + + def get_real_video_url(self): + return self.video_url + + def get_title_content(self): + return self.title or "" + + def get_cover_photo_url(self): + return self.cover_url + + def get_author_info(self): + return self.author + + def get_image_list(self): + return self.image_list diff --git a/tests/live_parser_samples.json b/tests/live_parser_samples.json index 584bce0..ae0f756 100644 --- a/tests/live_parser_samples.json +++ b/tests/live_parser_samples.json @@ -28,6 +28,7 @@ {"platform": "虎牙", "url": "https://hy.fan/v3cwMK", "media_types": ["video"], "expected_fields": ["video", "cover", "title"], "note": "2026-08-27 已验证"}, {"platform": "西瓜视频", "url": "https://www.iesdouyin.com/xg/video/7676450021063735414/?app=video_article×tamp=1787834623&device_id=973518813013579&tt_from=copy_link&utm_source=copy_link&utm_medium=ios&utm_campaign=client_share&test_group=v1", "alternate_urls": ["https://v.douyin.com/Nid-fFF_sdI/"], "media_types": ["video"], "expected_fields": ["video", "cover", "title", "author"], "note": "2026-08-27 更新;App 短链会跳转到同类西瓜视频页面"}, {"platform": "豆包", "url": "https://www.doubao.com/video-sharing?share_id=41356597786354690&source_type=mobile&video_id=v0d69cg10004d6978e2ljht0i4fdpp00&share_scene=video_viewer", "media_types": ["video"], "expected_fields": ["video", "cover", "title", "author"], "note": "待人工复核"}, - {"platform": "通义千问", "url": "https://activity.qianwen.com/r/ai-studio-mobile/qwen-external-share?&shareId=ZeeOedXncnGlElkluRMA&authorId=OjTAcGHgZgyeCwY4jeMDuH9JkGZ10BNYFM1HfW4CcLhxRA%3D%3D&enter_from=create_share&fp_from=create_share&channel_from=qwen&image_index=0", "media_types": ["images"], "expected_fields": ["images", "cover", "title", "author"], "note": "2026-08-27 已验证"} + {"platform": "通义千问", "url": "https://activity.qianwen.com/r/ai-studio-mobile/qwen-external-share?&shareId=ZeeOedXncnGlElkluRMA&authorId=OjTAcGHgZgyeCwY4jeMDuH9JkGZ10BNYFM1HfW4CcLhxRA%3D%3D&enter_from=create_share&fp_from=create_share&channel_from=qwen&image_index=0", "media_types": ["images"], "expected_fields": ["images", "cover", "title", "author"], "note": "2026-08-27 已验证"}, + {"platform": "闲鱼", "url": "https://e.tb.cn/h.87fj9SNrqHW8kfC?tk=y1E5Tb4wkGd", "media_types": ["images"], "expected_fields": ["title"], "note": "2026-08-27 已验证"} ] } diff --git a/tests/test_xianyu_parser.py b/tests/test_xianyu_parser.py new file mode 100644 index 0000000..40757a6 --- /dev/null +++ b/tests/test_xianyu_parser.py @@ -0,0 +1,41 @@ +import unittest +from unittest.mock import Mock, patch + +from src.parsers.xianyu_parser import XianyuParser + + +class XianyuParserTest(unittest.TestCase): + def test_parses_xianyu_short_link(self): + page_html = """ + + + 闲鱼分享 + + + + + """ + + page_resp = Mock() + page_resp.raise_for_status.return_value = None + page_resp.text = page_html + + url = "https://e.tb.cn/h.87fj9SNrqHW8kfC?tk=y1E5Tb4wkGd" + with patch("requests.Session.get", return_value=page_resp): + parser = XianyuParser(url) + + self.assertEqual(parser.get_title_content(), "闲鱼商品 (商品ID: 967494320598, 标价: ¥12.2)") + + def test_invalid_url_handles_gracefully(self): + parser = XianyuParser("https://e.tb.cn/invalid") + self.assertEqual(parser.get_title_content(), "") + self.assertIsNone(parser.get_real_video_url()) + self.assertEqual(parser.get_image_list(), []) + self.assertIsNone(parser.get_cover_photo_url()) + + +if __name__ == "__main__": + unittest.main() diff --git a/utils/web_fetcher.py b/utils/web_fetcher.py index f1fd612..31b7bab 100755 --- a/utils/web_fetcher.py +++ b/utils/web_fetcher.py @@ -221,6 +221,15 @@ class UrlParser: preserved_params.append((key, value)) if preserved_params: address = f"{address}?{urlencode(preserved_params)}" + elif platform == "闲鱼": + query_params = parse_qs(parsed_url.query) + preserved_params = [] + for key in ("tk", "id", "price", "shareurl", "short_name", "sp_tk"): + value = query_params.get(key, [None])[0] + if value is not None: + preserved_params.append((key, value)) + if preserved_params: + address = f"{address}?{urlencode(preserved_params)}" return address @staticmethod