Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Economist for website changes

Browse Source 
Fixes #2019248 [error with Economist recipe](https://bugs.launchpad.net/calibre/+bug/2019248)
This commit is contained in:
Kovid Goyal 2023-05-12 07:55:31 +05:30
parent dcbb72a2b8
commit 9f3fa2a62d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
recipes/economist.recipe
View File

@ -269,6 +269,7 @@ class Economist(BasicNewsRecipe):
self.timefmt = ' [' + edition_date + ']' self.timefmt = ' [' + edition_date + ']'
else: else:
url = 'https://www.economist.com/printedition' url = 'https://www.economist.com/printedition'
# raw = open('/t/raw.html').read()
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
# with open('/t/raw.html', 'wb') as f: # with open('/t/raw.html', 'wb') as f:
# f.write(raw) # f.write(raw)
@ -293,18 +294,19 @@ class Economist(BasicNewsRecipe):
script_tag = soup.find("script", id="__NEXT_DATA__") script_tag = soup.find("script", id="__NEXT_DATA__")
if script_tag is not None: if script_tag is not None:
data = json.loads(script_tag.string) data = json.loads(script_tag.string)
# open('/t/raw.json', 'w').write(json.dumps(data, indent=2, sort_keys=True))
self.cover_url = safe_dict(data, "props", "pageProps", "content", "image", "main", "url", "canonical") self.cover_url = safe_dict(data, "props", "pageProps", "content", "image", "main", "url", "canonical")
self.log('Got cover:', self.cover_url) self.log('Got cover:', self.cover_url)
feeds_dict = defaultdict(list) feeds_dict = defaultdict(list)
for part in safe_dict(data, "props", "pageProps", "content", "hasPart", "parts"): for part in safe_dict(data, "props", "pageProps", "content", "hasPart", "parts"):
section = safe_dict(part, "print", "section", "headline") or '' section = safe_dict(part, "print", "section", "headline") or ''
title = safe_dict(part, "print", "headline") or '' title = safe_dict(part, "headline") or ''
url = safe_dict(part, "url", "canonical") or '' url = safe_dict(part, "url", "canonical") or ''
if not section or not title or not url: if not section or not title or not url:
continue continue
desc = safe_dict(part, "print", "description") or '' desc = safe_dict(part, "description") or ''
sub = safe_dict(part, "print", "subheadline") or '' sub = safe_dict(part, "subheadline") or ''
if sub and section != sub: if sub and section != sub:
desc = sub + ' :: ' + desc desc = sub + ' :: ' + desc
if '/interactive/' in url: if '/interactive/' in url:

8
recipes/economist_free.recipe
View File

@ -269,6 +269,7 @@ class Economist(BasicNewsRecipe):
self.timefmt = ' [' + edition_date + ']' self.timefmt = ' [' + edition_date + ']'
else: else:
url = 'https://www.economist.com/printedition' url = 'https://www.economist.com/printedition'
# raw = open('/t/raw.html').read()
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
# with open('/t/raw.html', 'wb') as f: # with open('/t/raw.html', 'wb') as f:
# f.write(raw) # f.write(raw)
@ -293,18 +294,19 @@ class Economist(BasicNewsRecipe):
script_tag = soup.find("script", id="__NEXT_DATA__") script_tag = soup.find("script", id="__NEXT_DATA__")
if script_tag is not None: if script_tag is not None:
data = json.loads(script_tag.string) data = json.loads(script_tag.string)
# open('/t/raw.json', 'w').write(json.dumps(data, indent=2, sort_keys=True))
self.cover_url = safe_dict(data, "props", "pageProps", "content", "image", "main", "url", "canonical") self.cover_url = safe_dict(data, "props", "pageProps", "content", "image", "main", "url", "canonical")
self.log('Got cover:', self.cover_url) self.log('Got cover:', self.cover_url)
feeds_dict = defaultdict(list) feeds_dict = defaultdict(list)
for part in safe_dict(data, "props", "pageProps", "content", "hasPart", "parts"): for part in safe_dict(data, "props", "pageProps", "content", "hasPart", "parts"):
section = safe_dict(part, "print", "section", "headline") or '' section = safe_dict(part, "print", "section", "headline") or ''
title = safe_dict(part, "print", "headline") or '' title = safe_dict(part, "headline") or ''
url = safe_dict(part, "url", "canonical") or '' url = safe_dict(part, "url", "canonical") or ''
if not section or not title or not url: if not section or not title or not url:
continue continue
desc = safe_dict(part, "print", "description") or '' desc = safe_dict(part, "description") or ''
sub = safe_dict(part, "print", "subheadline") or '' sub = safe_dict(part, "subheadline") or ''
if sub and section != sub: if sub and section != sub:
desc = sub + ' :: ' + desc desc = sub + ' :: ' + desc
if '/interactive/' in url: if '/interactive/' in url: