From 812cf96bc53bfc3edab76ffdd28fffe0b41a3f9a Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Mon, 30 Sep 2024 10:05:02 +0530
Subject: [PATCH] ...
---
recipes/nytfeeds.recipe | 32 ++++++++--------------
src/calibre/web/site_parsers/nytimes.py | 36 +++++++++----------------
2 files changed, 24 insertions(+), 44 deletions(-)
diff --git a/recipes/nytfeeds.recipe b/recipes/nytfeeds.recipe
index 0ac1ed5fcd..6214051f19 100644
--- a/recipes/nytfeeds.recipe
+++ b/recipes/nytfeeds.recipe
@@ -109,11 +109,12 @@ def parse_cnt(cnt):
yield ''.join(parse_fmt_type(cnt))
else:
for cnt_ in cnt[k]:
- yield from parse_types(cnt_)
+ yield ''.join(parse_types(cnt_))
if isinstance(cnt[k], dict):
- yield from parse_types(cnt[k])
- if cnt.get('text') and 'formats' not in cnt:
- yield cnt['text']
+ yield ''.join(parse_types(cnt[k]))
+ if cnt.get('text') and 'formats' not in cnt and 'content' not in cnt:
+ if isinstance(cnt['text'], str):
+ yield cnt['text']
def parse_types(x):
typename = x.get('__typename', '')
@@ -141,9 +142,6 @@ def parse_types(x):
elif typename == 'RuleBlock':
yield '
'
- elif typename in {'ImageBlock', 'VideoBlock', 'InteractiveBlock'}:
- yield "".join(parse_types(x['media']))
-
elif typename == 'Image':
yield "".join(parse_image(x))
@@ -161,23 +159,15 @@ def parse_types(x):
elif typename == 'ListItemBlock':
yield f'{"".join(parse_cnt(x))}'
- elif typename == 'CapsuleBlock':
- if x['capsuleContent'].get('body'):
- yield "".join(parse_cnt(x['capsuleContent']['body']))
- elif typename == 'Capsule':
- yield "".join(parse_cnt(x['body']))
-
- elif typename in {
- 'TextInline', 'TextOnlyDocumentBlock', 'DocumentBlock',
- 'SummaryBlock', 'VisualStackBlock'
- }:
+ elif typename == 'TextInline':
yield "".join(parse_cnt(x))
+ elif typename in {'DetailBlock', 'TextRunKV'}:
+ yield f'{"".join(parse_cnt(x))}
'
+
elif typename and typename not in {'RelatedLinksBlock', 'Dropzone'}:
- if x.get('media'):
- yield "".join(parse_types(x['media']))
- elif "".join(parse_cnt(x)).strip():
- yield f'{"".join(parse_cnt(x))}
'
+ if "".join(parse_cnt(x)).strip():
+ yield "".join(parse_cnt(x))
def article_parse(data):
yield ""
diff --git a/src/calibre/web/site_parsers/nytimes.py b/src/calibre/web/site_parsers/nytimes.py
index b82f7a124b..eeefb3c51c 100644
--- a/src/calibre/web/site_parsers/nytimes.py
+++ b/src/calibre/web/site_parsers/nytimes.py
@@ -9,7 +9,7 @@ from xml.sax.saxutils import escape, quoteattr
from calibre.utils.iso8601 import parse_iso8601
-module_version = 7 # needed for live updates
+module_version = 8 # needed for live updates
pprint
@@ -111,11 +111,12 @@ def parse_cnt(cnt):
yield ''.join(parse_fmt_type(cnt))
else:
for cnt_ in cnt[k]:
- yield from parse_types(cnt_)
+ yield ''.join(parse_types(cnt_))
if isinstance(cnt[k], dict):
- yield from parse_types(cnt[k])
- if cnt.get('text') and 'formats' not in cnt:
- yield cnt['text']
+ yield ''.join(parse_types(cnt[k]))
+ if cnt.get('text') and 'formats' not in cnt and 'content' not in cnt:
+ if isinstance(cnt['text'], str):
+ yield cnt['text']
def parse_types(x):
typename = x.get('__typename', '')
@@ -143,9 +144,6 @@ def parse_types(x):
elif typename == 'RuleBlock':
yield '
'
- elif typename in {'ImageBlock', 'VideoBlock', 'InteractiveBlock'}:
- yield "".join(parse_types(x['media']))
-
elif typename == 'Image':
yield "".join(parse_image(x))
@@ -161,25 +159,17 @@ def parse_types(x):
elif typename == 'ListBlock':
yield f''
elif typename == 'ListItemBlock':
- yield f'{"".join(parse_cnt(x))}'
+ yield f'\n{"".join(parse_cnt(x))}'
- elif typename == 'CapsuleBlock':
- if x['capsuleContent'].get('body'):
- yield "".join(parse_cnt(x['capsuleContent']['body']))
- elif typename == 'Capsule':
- yield "".join(parse_cnt(x['body']))
-
- elif typename in {
- 'TextInline', 'TextOnlyDocumentBlock', 'DocumentBlock',
- 'SummaryBlock', 'VisualStackBlock'
- }:
+ elif typename == 'TextInline':
yield "".join(parse_cnt(x))
+ elif typename in {'DetailBlock', 'TextRunKV'}:
+ yield f'{"".join(parse_cnt(x))}
'
+
elif typename and typename not in {'RelatedLinksBlock', 'Dropzone'}:
- if x.get('media'):
- yield "".join(parse_types(x['media']))
- elif "".join(parse_cnt(x)).strip():
- yield f'{"".join(parse_cnt(x))}
'
+ if "".join(parse_cnt(x)).strip():
+ yield "".join(parse_cnt(x))
def article_parse(data):
yield ""