fix/channel_playlist_parsing

examples/ch_playlists.py

@@ -4,6 +4,7 @@
 c = Channel(url)
 print(c.videos_url)
 print(c.vanity_url)
+print(c.playlist_urls)
 print(c.video_urls)
 for v in c.videos:
  print(v)

examples/search.py

@@ -2,14 +2,15 @@
 from tutubo.models import *
 
 
-def search(query, parse=False, max_res=50):
+def search(query, parse=False, max_res=50, live=False):
  res = {
  'channels': [],
  'playlists': [],
  'mix': [],
  'related_queries': [],
  'related_videos': [],
- 'videos': []
+ 'videos': [],
+ 'live': []
  }
  for v in search_yt(query, parse=parse, max_res=max_res, as_dict=False):
  if isinstance(v, YoutubeMixPreview):
@@ -22,13 +23,17 @@ def search(query, parse=False, max_res=50):
  res["playlists"].append(v.as_dict)
  elif isinstance(v, RelatedVideoPreview) or isinstance(v, RelatedVideo):
  res["related_videos"].append(v.as_dict)
- else:
- res["videos"].append(v.as_dict)
+ elif isinstance(v, VideoPreview):
+ if v.is_live:
+ res["live"].append(v.as_dict)
+ else:
+ res["videos"].append(v.as_dict)
  return res
 
+
 from pprint import pprint
 
-res = search("rob zombie", parse=False, max_res=50)
+res = search("Shout TV live", parse=False, max_res=50)
 
 pprint(res)
 """

tutubo/models.py

@@ -196,6 +196,10 @@ def length(self):
  60 * 60 * int(h)
  return 0
 
+ @property
+ def is_live(self) -> bool:
+ return self.length == 0
+
  @property
  def thumbnail_url(self):
  return f"https://img.youtube.com/vi/{self.video_id}/default.jpg"
@@ -371,16 +375,26 @@ def _extract_playlists(raw_json: str) -> Tuple[List[str], Optional[str]]:
 
  # this is the json tree structure, if the json was extracted from
  # html
+ playlists = []
  try:
- playlists = initial_data["contents"][
- "twoColumnBrowseResultsRenderer"][
- "tabs"][2]["tabRenderer"]["content"][
- "sectionListRenderer"]["contents"][0][
- "itemSectionRenderer"]["contents"][0][
- 'shelfRenderer']["content"][
- 'horizontalListRenderer']["items"]
+ tabs = initial_data["contents"]["twoColumnBrowseResultsRenderer"]["tabs"]
+ for t in tabs:
+ if "content" not in t["tabRenderer"]:
+ continue
+ data = t["tabRenderer"]["content"]
+ if "sectionListRenderer" not in t["tabRenderer"]["content"]:
+ continue
+ for c in data["sectionListRenderer"]["contents"][0]["itemSectionRenderer"]["contents"]:
+ if 'shelfRenderer' in c:
+ playlists = c['shelfRenderer']["content"]['horizontalListRenderer']["items"]
+ break
+ elif 'gridRenderer' in c:
+ playlists = c['gridRenderer']["items"]
+ break
+ if playlists:
+ break
  except (KeyError, IndexError, TypeError):
- playlists = []
+ pass
 
  continuation = None
  # remove duplicates