]*id=[\'"]([^\'"]+)[\'"]', raw_html, re.I)
+
+ if embedded_vids:
+ if not self.vid:
+ self.vid = embedded_vids[0]
+ for vid in embedded_vids:
+ self._fetch_video_url_by_vid(vid)
+ if self.video_url and self.video_url not in self.video_list:
+ self.video_list.append(self.video_url)
+
+ break
+ except Exception as e:
+ logger.warning("Failed to fetch article info for Yangshipin article %s from %s: %s", article_id, api_url, e)
+
def _parse(self):
if not self.real_url:
return
- # 尝试先从 URL 中提取 vid
+ # 尝试先从 URL 中提取 vid 与 article_id
parsed_url = urlparse(self.real_url)
qs = parse_qs(parsed_url.query)
self.vid = qs.get("vid", [None])[0]
+ self.article_id = qs.get("articleid", [None])[0] or qs.get("articleId", [None])[0] or qs.get("id", [None])[0]
html = self.fetch_html_content()
if not html:
logger.warning("Failed to fetch HTML content for Yangshipin URL: %s", self.real_url)
- if self.vid:
+ if self.article_id:
+ self._fetch_article_info(self.article_id)
+ elif self.vid:
self._fetch_video_url_by_vid(self.vid)
return
@@ -155,12 +265,25 @@ class YangshipinParser(BaseParser):
qs = parse_qs(parsed_url.query)
if not self.vid or self.vid == "5Sqx":
self.vid = qs.get("vid", [None])[0]
+ if not self.article_id:
+ self.article_id = qs.get("articleid", [None])[0] or qs.get("articleId", [None])[0] or qs.get("id", [None])[0]
html = self.fetch_html_content()
if not html:
- if self.vid:
+ if self.article_id:
+ self._fetch_article_info(self.article_id)
+ elif self.vid:
self._fetch_video_url_by_vid(self.vid)
return
+ # 若目标为文章页,直接调用文章接口解析
+ if not self.article_id and "article" in parsed_url.path:
+ article_match = re.search(r'article(?:id)?=([0-9a-zA-Z_]+)', self.real_url)
+ if article_match:
+ self.article_id = article_match.group(1)
+
+ if self.article_id:
+ self._fetch_article_info(self.article_id)
+
try:
# 1. 尝试从横屏视频 STATE 提取 (__STATE_video__)
data_vid = self._extract_state_json(html, "window.__STATE_video__")
@@ -168,11 +291,13 @@ class YangshipinParser(BaseParser):
sv = data_vid.get("payloads", {}).get("sharevideo", {})
if not self.vid:
self.vid = sv.get("vid")
- self.title = (sv.get("title") or "").strip()
- self.cover_url = sv.get("cover_pic")
+ if not self.title:
+ self.title = (sv.get("title") or "").strip()
+ if not self.cover_url:
+ self.cover_url = sv.get("cover_pic")
om_info = sv.get("om_info", {})
author_name = om_info.get("title")
- if author_name:
+ if author_name and not self.author:
self.author = {
"name": author_name,
"avatar": None,
@@ -194,7 +319,7 @@ class YangshipinParser(BaseParser):
or vd.get("poster", {}).get("poster", {}).get("imageUrl")
)
actor = vd.get("detailFollowItem", {}).get("actorItem", {})
- if actor:
+ if actor and not self.author:
nick_name = actor.get("nickName", {}).get("text")
head_url = actor.get("headUrl")
if nick_name or head_url:
@@ -218,7 +343,7 @@ class YangshipinParser(BaseParser):
if og_img and og_img.get("content"):
self.cover_url = og_img["content"].strip()
- if not self.vid:
+ if not self.vid and not self.article_id:
vid_match = re.search(r'[?&]vid=([0-9a-zA-Z_]+)', self.real_url) or re.search(r'["\']vid["\']\s*:\s*["\']([0-9a-zA-Z_]+)["\']', html)
if vid_match:
self.vid = vid_match.group(1)
@@ -227,13 +352,13 @@ class YangshipinParser(BaseParser):
logger.exception("Error parsing Yangshipin page: %s", exc)
# 4. 根据提取到的 vid 请求视频播放地址
- if self.vid:
+ if self.vid and not self.video_url:
self._fetch_video_url_by_vid(self.vid)
if self.title:
self.title = re.sub(r'<[^>]+>', '', self.title).strip()
- if not self.video_url and self.cover_url and self.cover_url not in self.image_list:
+ if not self.video_url and not self.image_list and self.cover_url:
self.image_list.append(self.cover_url)
def _extract_state_json(self, html, state_key):
@@ -258,11 +383,20 @@ class YangshipinParser(BaseParser):
def get_title_content(self):
return self.title or ""
+ def get_description(self):
+ return self.description
+
def get_cover_photo_url(self):
return self.cover_url
def get_author_info(self):
return self.author
+ def get_audio_url(self):
+ return self.audio_url
+
def get_image_list(self):
return self.image_list
+
+ def get_video_list(self):
+ return self.video_list
diff --git a/tests/live_parser_samples.json b/tests/live_parser_samples.json
index b92eb44..0a7fc5f 100644
--- a/tests/live_parser_samples.json
+++ b/tests/live_parser_samples.json
@@ -4571,6 +4571,21 @@
"note": "2026-09-06 已验证: 央视频短链与微视频详情",
"pattern": "微视频及短剧详情"
},
+ {
+ "platform": "央视频",
+ "url": "https://www.yspapp.cn/6j3j",
+ "media_types": [
+ "images"
+ ],
+ "expected_fields": [
+ "cover",
+ "title",
+ "images",
+ "author"
+ ],
+ "note": "2026-09-20 已验证: 央视频图文资讯与新闻文章",
+ "pattern": "图文资讯与文章详情"
+ },
{
"platform": "豆包",
"url": "https://www.doubao.com/music-sharing?vid=v02292g10006dadu4kq7dld48hgk0dn0&share_id=55311664453668866",
diff --git a/tests/test_yangshipin_parser.py b/tests/test_yangshipin_parser.py
index d0e740e..3accbea 100644
--- a/tests/test_yangshipin_parser.py
+++ b/tests/test_yangshipin_parser.py
@@ -148,14 +148,90 @@ class YangshipinParserTest(unittest.TestCase):
self.assertEqual(parser.get_cover_photo_url(), "https://jietufengmian.yangshipin.cn/cover3.jpg")
self.assertEqual(parser.get_image_list(), ["https://jietufengmian.yangshipin.cn/cover3.jpg"])
- def test_handles_empty_or_broken_html(self):
- with patch.object(YangshipinParser, "fetch_html_content", return_value="404 Not Found"), \
- patch.object(YangshipinParser, "_fetch_video_url_by_vid", return_value=None):
- parser = YangshipinParser("https://m.yangshipin.cn/video?vid=empty")
- self.assertEqual(parser.get_title_content(), "")
- self.assertIsNone(parser.get_cover_photo_url())
- self.assertIsNone(parser.get_author_info())
- self.assertEqual(parser.get_image_list(), [])
+ def test_parses_article_successfully(self):
+ meta_html = """
+
+
+
+ 央视频
+ """
+ article_page_html = "文章"
+ mock_article_resp = MagicMock()
+ mock_article_resp.status_code = 200
+ mock_article_resp.json.return_value = {
+ "data": {
+ "errCode": 0,
+ "head": {
+ "title": "亚运乒乓球签表:上届冠亚军孙颖莎早田希娜同半区",
+ "source": "体坛网",
+ "publishTime": "2026-09-18 21:04",
+ "coverImage": "https://jietufengmian.yangshipin.cn/cover_article.jpg"
+ },
+ "content": {
+ "content": "体坛周报全媒体原创
北京时间9月18日晚上,2026爱知-名古屋亚运会乒乓球项目各项签表正式出炉。
",
+ "images": [
+ "https://jietufengmian.yangshipin.cn/img1.jpg",
+ "https://jietufengmian.yangshipin.cn/img2.jpg"
+ ]
+ }
+ },
+ "ret": 0
+ }
+
+ with patch.object(YangshipinParser, "fetch_html_content", side_effect=[meta_html, article_page_html]), \
+ patch("requests.Session.get", return_value=mock_article_resp):
+ parser = YangshipinParser("https://www.yspapp.cn/6j3j")
+ self.assertEqual(parser.get_title_content(), "亚运乒乓球签表:上届冠亚军孙颖莎早田希娜同半区")
+ self.assertEqual(parser.get_cover_photo_url(), "https://jietufengmian.yangshipin.cn/cover_article.jpg")
+ self.assertEqual(parser.get_author_info(), {"name": "体坛网", "avatar": None})
+ self.assertEqual(
+ parser.get_description(),
+ "体坛周报全媒体原创\n\n北京时间9月18日晚上,2026爱知-名古屋亚运会乒乓球项目各项签表正式出炉。"
+ )
+ self.assertEqual(
+ parser.get_image_list(),
+ [
+ "https://jietufengmian.yangshipin.cn/img1.jpg",
+ "https://jietufengmian.yangshipin.cn/img2.jpg"
+ ]
+ )
+ self.assertIsNone(parser.get_real_video_url())
+ self.assertIsNone(parser.get_audio_url())
+
+ def test_parses_article_with_embedded_video_and_audio(self):
+ mock_article_resp = MagicMock()
+ mock_article_resp.status_code = 200
+ mock_article_resp.json.return_value = {
+ "data": {
+ "errCode": 0,
+ "head": {
+ "title": "新闻联播重点快讯",
+ "source": "央视新闻",
+ "coverImage": "https://jietufengmian.yangshipin.cn/cover_news.jpg"
+ },
+ "content": {
+ "content": "今日新闻要点如下:
",
+ "images": []
+ },
+ "audioCapsule": {
+ "audioUrl": "https://audio.ysp.cctv.cn/news.mp3"
+ }
+ },
+ "ret": 0
+ }
+
+ def mock_fetch_video(self, vid):
+ self.video_url = f"https://mp4playcloud-cdn.ysp.cctv.cn/{vid}.mp4"
+
+ with patch.object(YangshipinParser, "fetch_html_content", return_value=""), \
+ patch("requests.Session.get", return_value=mock_article_resp), \
+ patch.object(YangshipinParser, "_fetch_video_url_by_vid", side_effect=mock_fetch_video, autospec=True):
+ parser = YangshipinParser("https://m.yangshipin.cn/static/article.html?articleid=art123")
+ self.assertEqual(parser.get_title_content(), "新闻联播重点快讯")
+ self.assertEqual(parser.get_author_info(), {"name": "央视新闻", "avatar": None})
+ self.assertEqual(parser.get_audio_url(), "https://audio.ysp.cctv.cn/news.mp3")
+ self.assertEqual(parser.get_real_video_url(), "https://mp4playcloud-cdn.ysp.cctv.cn/v00000embedded.mp4")
+ self.assertEqual(parser.get_video_list(), ["https://mp4playcloud-cdn.ysp.cctv.cn/v00000embedded.mp4"])
if __name__ == "__main__":
diff --git a/utils/web_fetcher.py b/utils/web_fetcher.py
index 9d09403..81523d1 100755
--- a/utils/web_fetcher.py
+++ b/utils/web_fetcher.py
@@ -476,7 +476,7 @@ class UrlParser:
elif platform == "央视频":
query_params = parse_qs(parsed_url.query)
preserved_params = []
- for key in ("vid", "cid", "type", "serverFrom"):
+ for key in ("vid", "cid", "type", "serverFrom", "articleid", "articleId", "id"):
value = query_params.get(key, [None])[0]
if value is not None:
preserved_params.append((key, value))
@@ -586,7 +586,7 @@ class UrlParser:
params_item_id = query_params.get('item_id', [None])[0]
if params_item_id:
return params_item_id
- params_article_id = query_params.get('articleId', [None])[0]
+ params_article_id = query_params.get('articleId', [None])[0] or query_params.get('articleid', [None])[0]
if params_article_id:
return params_article_id
params_guid = query_params.get('guid', [None])[0]