✨ feat: support acg_video

README.md

@@ -28,3 +28,8 @@ yutto -q 64 get https://www.bilibili.com/bangumi/play/ep395211
 ## TODO List
 
 -  [ ] 好多，不知道该写些啥，等剩余任务较少时候再来写吧……
+
+## References
+
+-  https://github.com/SigureMo/bilili
+-  https://github.com/changmenseng/AsyncBilibiliDownloader

yutto/__main__.py

@@ -32,12 +32,13 @@ def main():
     parser.add_argument("--only-video", dest="require_audio", action="store_false", help="只下载视频")
     parser.add_argument("--only-audio", dest="require_video", action="store_false", help="只下载音频")
     parser.add_argument("--danmaku", default="xml", choices=["xml", "ass", "no"], help="弹幕类型，no 为不生成弹幕")
-    parser.add_argument("-b", "--block-size", default=1.0, type=float, help="分块下载时各块大小，单位为 MiB，默认为 1MiB")
+    parser.add_argument("-b", "--block-size", default=0.5, type=float, help="分块下载时各块大小，单位为 MiB，默认为 0.5MiB")
     parser.add_argument("-w", "--overwrite", action="store_true", help="强制覆盖已下载内容")
     parser.add_argument("-x", "--proxy", default="auto", help="设置代理（auto 为系统代理、no 为不使用代理、当然也可以设置代理值）")
     parser.add_argument("-d", "--dir", default="", help="下载目录")
     parser.add_argument("-c", "--sessdata", default="", help="Cookies 中的 SESSDATA 字段")
     parser.add_argument("--path-pattern", default="{auto}", help="多级目录的存储路径 Pattern")
+    parser.add_argument("--no-subtitle", action="store_true", help="不生成字幕文件")
     parser.add_argument("--no-color", action="store_true", help="不使用颜色")
     parser.add_argument("--debug", action="store_true", help="启用 debug 模式")
     parser.set_defaults(action=run)

yutto/cli/get.py

@@ -1,16 +1,25 @@
 import argparse
-import aiohttp
-from yutto.processor.crawler import gen_cookies, gen_headers
-from yutto.utils.functiontools.sync import sync
+import os
 import sys
 
+import aiohttp
+
+from yutto.api.acg_video import get_acg_video_playurl, get_acg_video_title, get_acg_video_list
+from yutto.api.bangumi import get_bangumi_list, get_bangumi_playurl, get_bangumi_title, get_season_id_by_episode_id
+from yutto.api.types import AId, AvId, BvId, CId, EpisodeId, MediaId, SeasonId
+from yutto.processor.crawler import gen_cookies, gen_headers
 from yutto.processor.downloader import download_video
-from yutto.api.bangumi import get_bangumi_playurl, get_bangumi_title, get_season_id_by_episode_id, get_bangumi_list
-from yutto.api.acg_video import get_acg_video_title, get_acg_video_playurl
-from yutto.api.types import AvId, AId, BvId, EpisodeId, MediaId, SeasonId, CId
-from yutto.processor.urlparser import regexp_bangumi_ep
-from yutto.utils.console.logger import Logger
+from yutto.processor.urlparser import (
+    regexp_acg_video_av,
+    regexp_acg_video_av_short,
+    regexp_acg_video_bv,
+    regexp_acg_video_bv_short,
+    regexp_bangumi_ep,
+    regexp_bangumi_ep_short,
+)
 from yutto.utils.console.formatter import repair_filename
+from yutto.utils.console.logger import Badge, Logger
+from yutto.utils.functiontools.sync import sync
 
 
 def add_get_arguments(parser: argparse.ArgumentParser):
@@ -20,10 +29,17 @@ def add_get_arguments(parser: argparse.ArgumentParser):
 
 @sync
 async def run(args: argparse.Namespace):
+    # args.sessdata = "0a7f9758%2C1629361847%2Ca86ac*21"
+    # # args.sessdata = ""
+    # sessdata = "0a7f9758%2C1629361847%2Ca86ac*21"
+    # # sessdata = "dfasdlfsa"
     async with aiohttp.ClientSession(
-        headers=gen_headers(), cookies=gen_cookies(args.sessdata), timeout=aiohttp.ClientTimeout(total=5)
+        headers=gen_headers(),
+        cookies=gen_cookies(args.sessdata),
+        cookie_jar=aiohttp.DummyCookieJar(),
+        timeout=aiohttp.ClientTimeout(total=5),
     ) as session:
-        if match_obj := regexp_bangumi_ep.match(args.url):
+        if (match_obj := regexp_bangumi_ep.match(args.url)) or (match_obj := regexp_bangumi_ep_short.match(args.url)):
             episode_id = EpisodeId(match_obj.group("episode_id"))
             season_id = await get_season_id_by_episode_id(session, episode_id)
             bangumi_list = await get_bangumi_list(session, season_id)
@@ -37,7 +53,27 @@ async def run(args: argparse.Namespace):
                 Logger.error("在列表中未找到该剧集")
                 sys.exit(1)
             videos, audios = await get_bangumi_playurl(session, avid, episode_id, cid)
-            # title = await get_bangumi_title(session, season_id)
+            title = await get_bangumi_title(session, season_id)
+            Logger.custom(title, Badge("番剧", fore="black", back="cyan"))
+        elif (
+            (match_obj := regexp_acg_video_av.match(args.url))
+            or (match_obj := regexp_acg_video_av_short.match(args.url))
+            or (match_obj := regexp_acg_video_bv.match(args.url))
+            or (match_obj := regexp_acg_video_bv_short.match(args.url))
+        ):
+            page: int = 1
+            if "aid" in match_obj.groupdict().keys():
+                avid = AId(match_obj.group("aid"))
+            else:
+                avid = BvId(match_obj.group("bvid"))
+            if match_obj.group("page") is not None:
+                page = int(match_obj.group("page"))
+            acg_video_list = await get_acg_video_list(session, avid)
+            cid = acg_video_list[page - 1]["cid"]
+            filename = acg_video_list[page - 1]["name"]
+            videos, audios = await get_acg_video_playurl(session, avid, cid)
+            title = await get_acg_video_title(session, avid)
+            Logger.custom(title, Badge("投稿视频", fore="black", back="cyan"))
         else:
             Logger.error("url 不正确～")
             sys.exit(1)

yutto/processor/downloader.py

@@ -61,7 +61,7 @@ async def download_video(
 ):
     video_path = os.path.join(output_dir, file_name + "_video.m4s")
     audio_path = os.path.join(output_dir, file_name + "_audio.m4s")
-    output_path = os.path.join(output_dir, file_name + "{output_format}")
+    output_path_template = os.path.join(output_dir, file_name + "{output_format}")
     ffmpeg = FFmpeg()
 
     # TODO: 显示全部 Videos、Audios 信息
@@ -69,6 +69,12 @@ async def download_video(
     audio = select_audio(audios, options["require_audio"], options["audio_quality"], options["audio_download_codec"])
     # TODO: 显示被选中的 Video、Audio 信息
 
+    output_format = ".mp4" if video is not None else ".aac"
+    output_path = output_path_template.format(output_format=output_format)
+    if not options["overwrite"] and os.path.exists(output_path):
+        Logger.info("文件 {} 已存在".format(file_name))
+        return
+
     # idx_video = -1
     # if video is not None:
     #     idx_video = videos.index(video)
@@ -146,8 +152,8 @@ async def download_video(
             "-acodec", options["audio_save_codec"],
         ])
     args.extend(["-y"])
-    output_format = ".mp4" if video is not None else ".aac"
-    args.append(output_path.format(output_format=output_format))
+
+    args.append(output_path)
     Logger.debug("FFmpeg > ffmpeg {}".format(" ".join(args)))
     ffmpeg.exec(args)
     # fmt: on

yutto/processor/urlparser.py

@@ -1,12 +1,12 @@
 import re
 
 # avid
-regexp_acg_video_av = re.compile(r"https?://(www\.|m\.)?bilibili\.com/video/av(?P<avid>\d+)")
-regexp_acg_video_av_short = re.compile(r"https?://b23\.tv/av(?P<avid>\d+)")
+regexp_acg_video_av = re.compile(r"https?://(www\.|m\.)?bilibili\.com/video/av(?P<aid>\d+)(\?p=(?P<page>\d+))?")
+regexp_acg_video_av_short = re.compile(r"https?://b23\.tv/av(?P<aid>\d+)(\?p=(?P<page>\d+))?")
 
 # bvid
-regexp_acg_video_bv = re.compile(r"https?://(www\.|m\.)?bilibili\.com/video/(?P<bvid>(bv|BV)\w+)")
-regexp_acg_video_bv_short = re.compile(r"https?://b23\.tv/(?P<bvid>(bv|BV)\w+)")
+regexp_acg_video_bv = re.compile(r"https?://(www\.|m\.)?bilibili\.com/video/(?P<bvid>(bv|BV)\w+)(\?p=(?P<page>\d+))?")
+regexp_acg_video_bv_short = re.compile(r"https?://b23\.tv/(?P<bvid>(bv|BV)\w+)(\?p=(?P<page>\d+))?")
 
 # media id
 regexp_bangumi_md = re.compile(r"https?://(www\.|m\.)?bilibili\.com/bangumi/media/md(?P<media_id>\d+)")