diff --git a/README.md b/README.md index 7db876f8..c3d3014e 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ -> [!IMPORTANT] +> [!IMPORTANT] > **收藏项目**，你将从 GitHub 上无延迟地接收所有发布通知～ ⭐️ starify @@ -27,14 +27,14 @@ | 平台 | 触发的消息形态 | 视频 | 图集 | 音频 | | ------- | --------------------------------- | ---- | ---- | ---- | | B 站 | av 号/BV 号/链接/短链/卡片/小程序 | ✅​ | ✅​ | ✅​ | -| 抖音 | 链接(分享链接，兼容电脑端链接) | ✅​ | ✅​ | ❌️ | -| 微博 | 链接(博文，视频，show, 文章) | ✅​ | ✅​ | ❌️ | -| 小红书 | 链接(含短链)/卡片 | ✅​ | ✅​ | ❌️ | -| 快手 | 链接(包含标准链接和短链) | ✅​ | ✅​ | ❌️ | -| acfun | 链接 | ✅​ | ❌️ | ❌️ | -| youtube | 链接(含短链) | ✅​ | ❌️ | ✅​ | -| tiktok | 链接 | ✅​ | ❌️ | ❌️ | -| twitter | 链接 | ✅​ | ✅​ | ❌️ | +| 抖音 | 链接(分享链接，兼容电脑端链接) | ✅​ | ✅​ | ❌️ | +| 微博 | 链接(博文，视频，show, 文章) | ✅​ | ✅​ | ❌️ | +| 小红书 | 链接(含短链)/卡片 | ✅​ | ✅​ | ❌️ | +| 快手 | 链接(包含标准链接和短链) | ✅​ | ✅​ | ❌️ | +| acfun | 链接 | ✅​ | ❌️ | ❌️ | +| youtube | 链接(含短链) | ✅​ | ❌️ | ✅​ | +| tiktok | 链接 | ✅​ | ❌️ | ❌️ | +| twitter | 链接 | ✅​ | ✅​ | ❌️ | 支持的链接，可参考 [测试链接](https://github.com/fllesser/nonebot-plugin-parser/blob/master/tests/others/test_urls.md) @@ -54,7 +54,7 @@ ## 💿 安装 -> [!Warning] +> [!Warning] > **如果你已经在使用 nonebot-plugin-resolver[2]，请在安装此插件前卸载**
@@ -339,18 +339,19 @@ class ExampleParser(BaseParser): # 4. 视频内容 author = self.create_author(author_name, avatar_url) - video = self.create_video_content(video_url, cover_url, duration) + video = self.create_video(video_url, cover_url, duration) # 5. 图集内容 image_urls = data.get("images") - images = self.create_image_contents(image_urls) + images = self.create_image(image_urls) # 6. 返回解析结果 return self.result( title=title, text=description, author=author, - contents=[video, *images], + video=video, + contents=[*images], timestamp=timestamp, url=f"https://example.com/video/{video_id}", ) @@ -375,7 +376,7 @@ author = self.create_author( ```python # 方式1：传入 URL，自动下载 -video = self.create_video_content( +video = self.create_video( url_or_task="https://example.com/video.mp4", cover_url="https://example.com/cover.jpg", # 可选 duration=120.5 # 可选，单位：秒 @@ -384,7 +385,7 @@ video = self.create_video_content( # 方式2：传入已创建的下载任务 from nonebot_plugin_parser.download import DOWNLOADER video_task = DOWNLOADER.download_video(url, ext_headers=self.headers) -video = self.create_video_content( +video = self.create_video( url_or_task=video_task, cover_url=cover_url, duration=duration @@ -395,7 +396,7 @@ video = self.create_video_content( ```python # 并发下载图集内容 -images = self.create_image_contents([ +images = self.create_images([ "https://example.com/img1.jpg", "https://example.com/img2.jpg", ]) @@ -418,5 +419,5 @@ real_url = await self.get_redirect_url( ## 🎉 致谢 -[nonebot-plugin-resolver](https://github.com/zhiyu1998/nonebot-plugin-resolver) -[parse-video-py](https://github.com/wujunwei928/parse-video-py) +- [nonebot-plugin-resolver](https://github.com/zhiyu1998/nonebot-plugin-resolver) | 初代解析插件 +- [parse-video-py](https://github.com/wujunwei928/parse-video-py) | 借鉴了抖音解析 diff --git a/src/nonebot_plugin_parser/parsers/acfun/__init__.py b/src/nonebot_plugin_parser/parsers/acfun/__init__.py index c9f04959..c336ddba 100644 --- a/src/nonebot_plugin_parser/parsers/acfun/__init__.py +++ b/src/nonebot_plugin_parser/parsers/acfun/__init__.py @@ -40,7 +40,7 @@ async def _parse(self, searched: re.Match[str]): video_name=f"acfun_{acid}.mp4", ) - video_content = self.create_video_content( + video_content = self.create_video( video_task, cover_url=video_info.coverUrl, ) diff --git a/src/nonebot_plugin_parser/parsers/base.py b/src/nonebot_plugin_parser/parsers/base.py index 4dc2a894..a7c36a2f 100644 --- a/src/nonebot_plugin_parser/parsers/base.py +++ b/src/nonebot_plugin_parser/parsers/base.py @@ -174,7 +174,7 @@ def create_author( return author - def create_video_content( + def create_video( self, url_or_task: str | Task[Path], cover_url: str | None = None, @@ -205,7 +205,7 @@ async def extract_cover(): duration=duration, ) - def create_image_contents( + def create_images( self, image_urls: list[str], ): @@ -216,12 +216,12 @@ def create_image_contents( contents.append(ImageContent(PathTask(task))) return contents - def create_image_content( + def create_image( self, url_or_task: str | Task[Path], alt: str | None = None, ): - """创建图片内容""" + """创建单个图片内容""" if isinstance(url_or_task, str): path_task = DOWNLOADER.download_img(url_or_task, ext_headers=self.headers) elif isinstance(url_or_task, Task): @@ -229,7 +229,7 @@ def create_image_content( return ImageContent(PathTask(path_task), alt=alt) - def create_audio_content( + def create_audio( self, url_or_task: str | Task[Path], duration: float = 0.0, diff --git a/src/nonebot_plugin_parser/parsers/bilibili/__init__.py b/src/nonebot_plugin_parser/parsers/bilibili/__init__.py index 1ab8f277..b029f539 100644 --- a/src/nonebot_plugin_parser/parsers/bilibili/__init__.py +++ b/src/nonebot_plugin_parser/parsers/bilibili/__init__.py @@ -148,7 +148,7 @@ async def download_video(): ) return path - video_content = self.create_video_content( + video_content = self.create_video( asyncio.create_task(download_video()), page_info.cover, page_info.duration, @@ -188,7 +188,7 @@ async def _parse_dynamic_info(self, dynamic_info: DynamicInfo): # 下载图片 author = self.create_author(dynamic_info.name, dynamic_info.avatar) contents: list[MediaContent] = [] - contents.extend(self.create_image_contents(dynamic_info.image_urls)) + contents.extend(self.create_images(dynamic_info.image_urls)) repost = None if dynamic_info.type == "DYNAMIC_TYPE_FORWARD" and dynamic_info.orig is not None: @@ -234,7 +234,7 @@ async def _parse_bilibli_api_opus(self, bili_opus: Opus): if isinstance(node, str): result.graphics.append(node) else: - result.graphics.append(self.create_image_content(node.url, alt=node.alt)) + result.graphics.append(self.create_image(node.url, alt=node.alt)) return result @@ -252,12 +252,12 @@ async def parse_live(self, room_id: int): # 下载封面 if cover := room_data.cover: cover_task = self.downloader.download_img(cover, ext_headers=self.headers) - contents.append(self.create_image_content(cover_task)) + contents.append(self.create_image(cover_task)) # 下载关键帧 if keyframe := room_data.keyframe: keyframe_task = self.downloader.download_img(keyframe, ext_headers=self.headers) - contents.append(self.create_image_content(keyframe_task)) + contents.append(self.create_image(keyframe_task)) author = self.create_author(room_data.name, room_data.avatar) @@ -288,7 +288,7 @@ async def parse_favlist(self, fav_id: int): graphics: list[str | ImageContent] = [] for fav in favdata.medias: - graphics.append(self.create_image_content(fav.cover, alt=fav.desc)) + graphics.append(self.create_image(fav.cover, alt=fav.desc)) graphics.append(fav.desc) return self.result( diff --git a/src/nonebot_plugin_parser/parsers/douyin/__init__.py b/src/nonebot_plugin_parser/parsers/douyin/__init__.py index 0cf859f4..a84cda7d 100644 --- a/src/nonebot_plugin_parser/parsers/douyin/__init__.py +++ b/src/nonebot_plugin_parser/parsers/douyin/__init__.py @@ -92,10 +92,10 @@ async def parse_video(self, url: str): # 添加图片内容 if image_urls := video_data.image_urls: - result.contents.extend(self.create_image_contents(image_urls)) + result.contents.extend(self.create_images(image_urls)) # 添加视频内容 elif video_url := video_data.video_url: - result.video = self.create_video_content( + result.video = self.create_video( video_url, video_data.cover_url, video_data.duration, @@ -130,8 +130,8 @@ async def parse_slides(self, video_id: str): # 优先取动图 if dynamic_urls := slides_data.dynamic_urls: for dynamic_url in dynamic_urls: - result.contents.append(self.create_video_content(dynamic_url)) + result.contents.append(self.create_video(dynamic_url)) elif image_urls := slides_data.image_urls: - result.contents.extend(self.create_image_contents(image_urls)) + result.contents.extend(self.create_images(image_urls)) return result diff --git a/src/nonebot_plugin_parser/parsers/kuaishou/__init__.py b/src/nonebot_plugin_parser/parsers/kuaishou/__init__.py index f5d35a98..aecafb59 100644 --- a/src/nonebot_plugin_parser/parsers/kuaishou/__init__.py +++ b/src/nonebot_plugin_parser/parsers/kuaishou/__init__.py @@ -64,10 +64,10 @@ async def _parse_v_kuaishou(self, searched: re.Match[str]): # 添加视频内容 if video_url := photo.video_url: - result.video = self.create_video_content(video_url, photo.cover_url, photo.duration) + result.video = self.create_video(video_url, photo.cover_url, photo.duration) # 添加图片内容 if img_urls := photo.img_urls: - result.contents.extend(self.create_image_contents(img_urls)) + result.contents.extend(self.create_images(img_urls)) return result diff --git a/src/nonebot_plugin_parser/parsers/nga.py b/src/nonebot_plugin_parser/parsers/nga.py index 385a07aa..a1199d05 100644 --- a/src/nonebot_plugin_parser/parsers/nga.py +++ b/src/nonebot_plugin_parser/parsers/nga.py @@ -125,7 +125,7 @@ async def _parse(self, searched: re.Match[str]): if paths := re.findall(r"\[img\]\.(.*?)\[\/img\]", line): for path in paths: img_url = self.build_img_url(path) - result.graphics.append(self.create_image_content(img_url)) + result.graphics.append(self.create_image(img_url)) else: # 去除其他标签, 仅保留文本 if clean_line := re.sub(r"\[[^\]]*?\]", "", line).strip(): diff --git a/src/nonebot_plugin_parser/parsers/task.py b/src/nonebot_plugin_parser/parsers/task.py index 9d0c3dc0..c71abac4 100644 --- a/src/nonebot_plugin_parser/parsers/task.py +++ b/src/nonebot_plugin_parser/parsers/task.py @@ -38,9 +38,7 @@ async def safe_get( @property async def uri(self) -> str | None: path = await self.safe_get() - if path is not None: - return path.as_uri() - return None + return path.as_uri() if path else None def __repr__(self) -> str: if self._path is not None: diff --git a/src/nonebot_plugin_parser/parsers/tiktok.py b/src/nonebot_plugin_parser/parsers/tiktok.py index 31310ec3..779c37db 100644 --- a/src/nonebot_plugin_parser/parsers/tiktok.py +++ b/src/nonebot_plugin_parser/parsers/tiktok.py @@ -22,7 +22,7 @@ async def _parse(self, searched: re.Match[str]): # 下载封面和视频 video = YTDLP_DOWNLOADER.download_video(url) - video_content = self.create_video_content( + video_content = self.create_video( video, video_info.thumbnail, duration=video_info.duration, diff --git a/src/nonebot_plugin_parser/parsers/twitter.py b/src/nonebot_plugin_parser/parsers/twitter.py index 922f05ba..54184477 100644 --- a/src/nonebot_plugin_parser/parsers/twitter.py +++ b/src/nonebot_plugin_parser/parsers/twitter.py @@ -82,17 +82,17 @@ def _collect_result(self, data: VxTwitterResponse) -> ParseResult: for media in data.media_extended: if media.type == "video": - result.video = self.create_video_content( + result.video = self.create_video( media.url, media.thumbnail_url, duration=media.duration, ) break elif media.type == "image": - result.contents.append(self.create_image_content(media.url)) + result.contents.append(self.create_image(media.url)) elif media.type == "gif": result.contents.append( - self.create_video_content( + self.create_video( media.url, media.thumbnail_url, duration=media.duration, @@ -161,12 +161,12 @@ def _parse_twitter_html(self, html_content: str) -> ParseResult: href = str(href) text = tag.get_text(strip=True) if "下载 MP4" in text: - result.video = self.create_video_content(href, cover_url) + result.video = self.create_video(href, cover_url) break elif "下载图片" in text: - result.contents.append(self.create_image_content(href)) + result.contents.append(self.create_image(href)) elif "下载 gif" in text: - result.contents.append(self.create_video_content(href)) + result.contents.append(self.create_video(href)) # 3. 提取标题 title_tag = soup.find("h3") diff --git a/src/nonebot_plugin_parser/parsers/weibo/__init__.py b/src/nonebot_plugin_parser/parsers/weibo/__init__.py index 00ed2549..9511fdd0 100644 --- a/src/nonebot_plugin_parser/parsers/weibo/__init__.py +++ b/src/nonebot_plugin_parser/parsers/weibo/__init__.py @@ -101,7 +101,7 @@ async def parse_article(self, _id: str): elif element.name == "img": src = element.get("src") if isinstance(src, str): - graphics.append(self.create_image_content(src)) + graphics.append(self.create_image(src)) author = self.create_author( data.userinfo.screen_name, @@ -140,7 +140,7 @@ async def parse_fid(self, fid: str): play_info.description, ) - video_content = self.create_video_content( + video_content = self.create_video( play_info.video_url, play_info.cover_url, duration=play_info.duration, @@ -211,7 +211,7 @@ def _collect_result(self, data: common.WeiboData): # 添加视频内容 if video_url := data.video_url: - result.video = self.create_video_content( + result.video = self.create_video( video_url, data.cover_url, data.duration, @@ -219,7 +219,7 @@ def _collect_result(self, data: common.WeiboData): # 添加图片内容 if image_urls := data.image_urls: - result.contents.extend(self.create_image_contents(image_urls)) + result.contents.extend(self.create_images(image_urls)) # 转发内容 if data.retweeted_status: diff --git a/src/nonebot_plugin_parser/parsers/xiaohongshu/__init__.py b/src/nonebot_plugin_parser/parsers/xiaohongshu/__init__.py index 1cf44ef3..e79b65ca 100644 --- a/src/nonebot_plugin_parser/parsers/xiaohongshu/__init__.py +++ b/src/nonebot_plugin_parser/parsers/xiaohongshu/__init__.py @@ -83,12 +83,11 @@ async def parse_explore(self, url: str, xhs_id: str): # 添加视频内容 if note_detail.is_video: - video_cover_duration = note_detail.video_cover_duration - result.video = self.create_video_content(*video_cover_duration) + result.video = self.create_video(*note_detail.video_cover_duration) # 添加图片内容 elif image_urls := note_detail.image_urls: - result.contents.extend(self.create_image_contents(image_urls)) + result.contents.extend(self.create_images(image_urls)) return result @@ -128,13 +127,13 @@ async def parse_discovery(self, url: str): else: cover_url = note_data.image_urls[0] - result.video = self.create_video_content( + result.video = self.create_video( video_url, cover_url, duration, ) elif img_urls := note_data.image_urls: - result.contents.extend(self.create_image_contents(img_urls)) + result.contents.extend(self.create_images(img_urls)) return result diff --git a/src/nonebot_plugin_parser/parsers/youtube/__init__.py b/src/nonebot_plugin_parser/parsers/youtube/__init__.py index d7a2ccb3..f42a5c61 100644 --- a/src/nonebot_plugin_parser/parsers/youtube/__init__.py +++ b/src/nonebot_plugin_parser/parsers/youtube/__init__.py @@ -39,13 +39,13 @@ async def parse_video(self, url: str): if video_info.duration <= pconfig.duration_maximum: video = YTDLP_DOWNLOADER.download_video(url, self.cookies_file) - result.video = self.create_video_content( + result.video = self.create_video( video, video_info.thumbnail, video_info.duration, ) else: - result.contents.extend(self.create_image_contents([video_info.thumbnail])) + result.contents.extend(self.create_images([video_info.thumbnail])) return result