MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-27 21:55:50 +01:00
Code Issues Projects Releases Wiki Activity

[youtube] Simplified renderer parsing

Browse Source
This commit is contained in:
pukkandan 2021-02-09 21:37:59 +05:30
parent a1b535bd75
commit 69184e4152
1 changed files with 35 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
youtube_dlc/extractor/youtube.py
View File

@ -2614,35 +2614,22 @@ def extract_entries(parent_renderer): # this needs to called again for continua
for isr_content in isr_contents: for isr_content in isr_contents:
if not isinstance(isr_content, dict): if not isinstance(isr_content, dict):
continue continue
renderer = isr_content.get('playlistVideoListRenderer')
if renderer: known_renderers = {
for entry in self._playlist_entries(renderer): 'playlistVideoListRenderer': self._playlist_entries,
yield entry 'gridRenderer': self._grid_entries,
continuation_list[0] = self._extract_continuation(renderer) 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
'backstagePostThreadRenderer': self._post_thread_entries,
'videoRenderer': lambda x: [self._video_entry(x)],
}
for key, renderer in isr_content.items():
if key not in known_renderers:
continue continue
renderer = isr_content.get('gridRenderer') for entry in known_renderers[key](renderer):
if renderer:
for entry in self._grid_entries(renderer):
yield entry
continuation_list[0] = self._extract_continuation(renderer)
continue
renderer = isr_content.get('shelfRenderer')
if renderer:
is_channels_tab = tab.get('title') == 'Channels'
for entry in self._shelf_entries(renderer, not is_channels_tab):
yield entry
continue
renderer = isr_content.get('backstagePostThreadRenderer')
if renderer:
for entry in self._post_thread_entries(renderer):
yield entry
continuation_list[0] = self._extract_continuation(renderer)
continue
renderer = isr_content.get('videoRenderer')
if renderer:
entry = self._video_entry(renderer)
if entry: if entry:
yield entry yield entry
continuation_list[0] = self._extract_continuation(renderer)
break
if not continuation_list[0]: if not continuation_list[0]:
continuation_list[0] = self._extract_continuation(is_renderer) continuation_list[0] = self._extract_continuation(is_renderer)
@ -2695,33 +2682,25 @@ def extract_entries(parent_renderer): # this needs to called again for continua
if not response: if not response:
break break
known_continuation_renderers = {
'playlistVideoListContinuation': self._playlist_entries,
'gridContinuation': self._grid_entries,
'itemSectionContinuation': self._post_thread_continuation_entries,
'sectionListContinuation': extract_entries, # for feeds
}
continuation_contents = try_get( continuation_contents = try_get(
response, lambda x: x['continuationContents'], dict) response, lambda x: x['continuationContents'], dict) or {}
if continuation_contents: continuation_renderer = None
continuation_renderer = continuation_contents.get('playlistVideoListContinuation') for key, value in continuation_contents.items():
if continuation_renderer: if key not in known_continuation_renderers:
for entry in self._playlist_entries(continuation_renderer):
yield entry
continuation = self._extract_continuation(continuation_renderer)
continue continue
continuation_renderer = continuation_contents.get('gridContinuation') continuation_renderer = value
if continuation_renderer:
for entry in self._grid_entries(continuation_renderer):
yield entry
continuation = self._extract_continuation(continuation_renderer)
continue
continuation_renderer = continuation_contents.get('itemSectionContinuation')
if continuation_renderer:
for entry in self._post_thread_continuation_entries(continuation_renderer):
yield entry
continuation = self._extract_continuation(continuation_renderer)
continue
continuation_renderer = continuation_contents.get('sectionListContinuation') # for feeds
if continuation_renderer:
continuation_list = [None] continuation_list = [None]
for entry in extract_entries(continuation_renderer): for entry in known_continuation_renderers[key](continuation_renderer):
yield entry yield entry
continuation = continuation_list[0] continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
break
if continuation_renderer:
continue continue
known_renderers = { known_renderers = {
@ -3102,7 +3081,7 @@ def _real_extract(self, url):
class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor): class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com searches' IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
# there doesn't appear to be a real limit, for example if you search for # there doesn't appear to be a real limit, for example if you search for
# 'python' you get more than 8.000.000 results # 'python' you get more than 8.000.000 results
_MAX_RESULTS = float('inf') _MAX_RESULTS = float('inf')
@ -3191,7 +3170,7 @@ class YoutubeSearchDateIE(YoutubeSearchIE):
class YoutubeSearchURLIE(YoutubeSearchIE): class YoutubeSearchURLIE(YoutubeSearchIE):
IE_DESC = 'YouTube.com searches, "ytsearch" keyword' IE_DESC = 'YouTube.com search URLs'
IE_NAME = YoutubeSearchIE.IE_NAME + '_url' IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
# _MAX_RESULTS = 100 # _MAX_RESULTS = 100