From 2fd06a4f6795346cceedb783f28225a388bb6dcd Mon Sep 17 00:00:00 2001
From: Riceball LEE <snowyu.lee@gmail.com>
Date: Wed, 15 Feb 2023 11:56:51 +0800
Subject: [PATCH] feat(bilibili): add support for first option

---
 src/you_get/extractor.py           |  8 ++++++++
 src/you_get/extractors/bilibili.py | 28 ++++++++++++++++++++++++----
 2 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/src/you_get/extractor.py b/src/you_get/extractor.py
index bd71717e72..27bbf32f3f 100644
--- a/src/you_get/extractor.py
+++ b/src/you_get/extractor.py
@@ -19,6 +19,9 @@ def __init__(self, *args):
             self.url = args[0]
 
 class VideoExtractor():
+    download_count = 0
+    skip_count = 0
+
     def __init__(self, *args):
         self.url = None
         self.title = None
@@ -177,6 +180,11 @@ def p_playlist(self, stream_id=None):
         print("videos:")
 
     def download(self, **kwargs):
+        self.__class__.download_count += 1
+        if self.__class__.skip_count and self.__class__.download_count < self.__class__.skip_count:
+            log.i("skipped({}): {}".format(self.__class__.download_count, self.title))
+            return
+
         if 'json_output' in kwargs and kwargs['json_output']:
             json_output.output(self)
         elif 'info_only' in kwargs and kwargs['info_only']:
diff --git a/src/you_get/extractors/bilibili.py b/src/you_get/extractors/bilibili.py
index 6335e6dd87..6a1ad44b27 100644
--- a/src/you_get/extractors/bilibili.py
+++ b/src/you_get/extractors/bilibili.py
@@ -649,6 +649,16 @@ def download_playlist_by_url(self, url, **kwargs):
             log.e('[Error] Unsupported URL pattern.')
             exit(1)
 
+        args = kwargs.get('args')
+        first = 0
+        if ('first' in args and args.first!= None):
+            first = int(args.first)
+            if first < 0: first = 0
+        if sort not in ['video', 'bangumi','bangumi_md','audio_menu']:
+            args.first = None
+            if first > 0:
+                self.__class__.skip_count = first
+
         # regular video
         if sort == 'video':
             initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)')  # FIXME
@@ -658,12 +668,16 @@ def download_playlist_by_url(self, url, **kwargs):
 
             if pn == len(initial_state['videoData']['pages']):
                 # non-interative video
-                for pi in range(1, pn + 1):
+                for pi in range(first+1, pn + 1):
                      purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi)
                      self.__class__().download_by_url(purl, **kwargs)
 
             else:
                 # interative video
+                if first > 0:
+                    args.first = None
+                    self.__class__.skip_count = first
+
                 search_node_list = []
                 download_cid_set = set([initial_state['videoData']['cid']])
                 params = {
@@ -720,7 +734,9 @@ def download_playlist_by_url(self, url, **kwargs):
             initial_state = json.loads(initial_state_text)
             epn, i = len(initial_state['epList']), 0
             for ep in initial_state['epList']:
-                i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
+                i += 1
+                if i <= first: continue
+                log.w('Extracting %s of %s videos ...' % (i, epn))
                 ep_id = ep['id']
                 epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id
                 self.__class__().download_by_url(epurl, **kwargs)
@@ -730,7 +746,9 @@ def download_playlist_by_url(self, url, **kwargs):
             initial_state = json.loads(initial_state_text)
             epn, i = len(initial_state['mediaInfo']['episodes']), 0
             for ep in initial_state['mediaInfo']['episodes']:
-                i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
+                i += 1
+                if i <= first: continue
+                log.w('Extracting %s of %s videos ...' % (i, epn))
                 ep_id = ep['ep_id']
                 epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id
                 self.__class__().download_by_url(epurl, **kwargs)
@@ -843,7 +861,9 @@ def download_playlist_by_url(self, url, **kwargs):
             menusong_info = json.loads(api_content)
             epn, i = len(menusong_info['data']['data']), 0
             for song in menusong_info['data']['data']:
-                i += 1; log.w('Extracting %s of %s songs ...' % (i, epn))
+                i += 1
+                if i <= first: continue
+                log.w('Extracting %s of %s songs ...' % (i, epn))
                 url = 'https://www.bilibili.com/audio/au%s' % song['id']
                 self.__class__().download_by_url(url, **kwargs)