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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-01-01 14:47:46 +05:30
commit 3032655349
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
3 changed files with 12 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
recipes/economist.recipe
View File

@ -205,6 +205,10 @@ class Economist(BasicNewsRecipe):
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
# open('/t/raw.html', 'wb').write(raw.encode('utf-8')) # open('/t/raw.html', 'wb').write(raw.encode('utf-8'))
root = parse(raw) root = parse(raw)
if '/interactive/' in url:
return '<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>' \
+ 'This article is supposed to be read in a browser' \
+ '</em></article></body></html>'
script = root.xpath('//script[@id="__NEXT_DATA__"]') script = root.xpath('//script[@id="__NEXT_DATA__"]')
if script: if script:
try: try:
@ -293,9 +297,6 @@ class Economist(BasicNewsRecipe):
sub = safe_dict(part, "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:
self.log('Skipping interactive article:', title, url)
continue
feeds_dict[section].append({"title": title, "url": url, "description": desc}) feeds_dict[section].append({"title": title, "url": url, "description": desc})
self.log(' ', title, url, '\n ', desc) self.log(' ', title, url, '\n ', desc)
return [(section, articles) for section, articles in feeds_dict.items()] return [(section, articles) for section, articles in feeds_dict.items()]

7
recipes/economist_free.recipe
View File

@ -205,6 +205,10 @@ class Economist(BasicNewsRecipe):
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
# open('/t/raw.html', 'wb').write(raw.encode('utf-8')) # open('/t/raw.html', 'wb').write(raw.encode('utf-8'))
root = parse(raw) root = parse(raw)
if '/interactive/' in url:
return '<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>' \
+ 'This article is supposed to be read in a browser' \
+ '</em></article></body></html>'
script = root.xpath('//script[@id="__NEXT_DATA__"]') script = root.xpath('//script[@id="__NEXT_DATA__"]')
if script: if script:
try: try:
@ -293,9 +297,6 @@ class Economist(BasicNewsRecipe):
sub = safe_dict(part, "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:
self.log('Skipping interactive article:', title, url)
continue
feeds_dict[section].append({"title": title, "url": url, "description": desc}) feeds_dict[section].append({"title": title, "url": url, "description": desc})
self.log(' ', title, url, '\n ', desc) self.log(' ', title, url, '\n ', desc)
return [(section, articles) for section, articles in feeds_dict.items()] return [(section, articles) for section, articles in feeds_dict.items()]

7
recipes/economist_world_ahead.recipe
View File

@ -201,6 +201,10 @@ class Economist(BasicNewsRecipe):
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
# open('/t/raw.html', 'wb').write(raw.encode('utf-8')) # open('/t/raw.html', 'wb').write(raw.encode('utf-8'))
root = parse(raw) root = parse(raw)
if '/interactive/' in url:
return '<html><body><article><h1>' + root.xpath('//h1')[0].text + '</h1><em>' \
+ 'This article is supposed to be read in a browser' \
+ '</em></article></body></html>'
script = root.xpath('//script[@id="__NEXT_DATA__"]') script = root.xpath('//script[@id="__NEXT_DATA__"]')
if script: if script:
try: try:
@ -281,9 +285,6 @@ class Economist(BasicNewsRecipe):
sub = safe_dict(part, "subheadline") or '' sub = safe_dict(part, "subheadline") or ''
if sub: if sub:
desc = sub + ' :: ' + desc desc = sub + ' :: ' + desc
if '/interactive/' in url:
self.log('\tSkipping interactive article:', title, url)
continue
self.log('\t', title, '\n\t', desc, '\n\t\t', url) self.log('\t', title, '\n\t', desc, '\n\t\t', url)
articles.append({'title': title, 'description':desc, 'url': url}) articles.append({'title': title, 'description':desc, 'url': url})
if articles: if articles: