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

Dont fail to download interactive aricles from the Economist

Browse Source 
They dont work well and look pretty awful, but better than nothing
This commit is contained in:
Kovid Goyal 2022-06-11 12:34:23 +05:30
parent bff96f44c2
commit 23e52f2cba
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 58 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/economist.recipe
View File

@ -53,9 +53,16 @@ def safe_dict(data, *names):
return ans
class JSONHasNoContent(ValueError):
pass
def load_article_from_json(raw, root):
data = json.loads(raw)['props']['pageProps']['content']
# open('/t/raw.json', 'w').write(json.dumps(data, indent=2, sort_keys=True))
# open('/t/raw.json', 'w').write(raw)
try:
data = json.loads(raw)['props']['pageProps']['content']
except KeyError as e:
raise JSONHasNoContent(e)
if isinstance(data, list):
data = data[0]
body = root.xpath('//body')[0]
@ -77,6 +84,20 @@ def load_article_from_json(raw, root):
process_node(node, article)
def cleanup_html_article(root):
main = root.xpath('//main')[0]
body = root.xpath('//body')[0]
for child in tuple(body):
body.remove(child)
body.append(main)
main.set('id', '')
main.tag = 'article'
for x in root.xpath('//*[@style]'):
x.set('style', '')
for x in root.xpath('//button'):
x.getparent().remove(x)
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
@ -104,6 +125,7 @@ class Economist(BasicNewsRecipe):
title = 'The Economist'
language = 'en'
encoding = 'utf-8'
__author__ = "Kovid Goyal"
description = (
@ -208,7 +230,10 @@ class Economist(BasicNewsRecipe):
root = parse(raw)
script = root.xpath('//script[@id="__NEXT_DATA__"]')
if script:
load_article_from_json(script[0].text, root)
try:
load_article_from_json(script[0].text, root)
except JSONHasNoContent:
cleanup_html_article(root)
for div in root.xpath('//div[@class="lazy-image"]'):
noscript = list(div.iter('noscript'))
if noscript and noscript[0].text:
@ -248,7 +273,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self):
# return [('Articles', [{'title':'test',
# 'url':'https://www.economist.com/economic-and-financial-indicators/2022/04/23/economic-data-commodities-and-markets'
# 'url':'https://www.economist.com/interactive/briefing/2022/06/11/huge-foundation-models-are-turbo-charging-ai-progress'
# }])]
if edition_date:
url = 'https://www.economist.com/weeklyedition/' + edition_date

33
recipes/economist_free.recipe
View File

@ -53,9 +53,16 @@ def safe_dict(data, *names):
return ans
class JSONHasNoContent(ValueError):
pass
def load_article_from_json(raw, root):
data = json.loads(raw)['props']['pageProps']['content']
# open('/t/raw.json', 'w').write(json.dumps(data, indent=2, sort_keys=True))
# open('/t/raw.json', 'w').write(raw)
try:
data = json.loads(raw)['props']['pageProps']['content']
except KeyError as e:
raise JSONHasNoContent(e)
if isinstance(data, list):
data = data[0]
body = root.xpath('//body')[0]
@ -77,6 +84,20 @@ def load_article_from_json(raw, root):
process_node(node, article)
def cleanup_html_article(root):
main = root.xpath('//main')[0]
body = root.xpath('//body')[0]
for child in tuple(body):
body.remove(child)
body.append(main)
main.set('id', '')
main.tag = 'article'
for x in root.xpath('//*[@style]'):
x.set('style', '')
for x in root.xpath('//button'):
x.getparent().remove(x)
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
@ -104,6 +125,7 @@ class Economist(BasicNewsRecipe):
title = 'The Economist'
language = 'en'
encoding = 'utf-8'
__author__ = "Kovid Goyal"
description = (
@ -208,7 +230,10 @@ class Economist(BasicNewsRecipe):
root = parse(raw)
script = root.xpath('//script[@id="__NEXT_DATA__"]')
if script:
load_article_from_json(script[0].text, root)
try:
load_article_from_json(script[0].text, root)
except JSONHasNoContent:
cleanup_html_article(root)
for div in root.xpath('//div[@class="lazy-image"]'):
noscript = list(div.iter('noscript'))
if noscript and noscript[0].text:
@ -248,7 +273,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self):
# return [('Articles', [{'title':'test',
# 'url':'https://www.economist.com/economic-and-financial-indicators/2022/04/23/economic-data-commodities-and-markets'
# 'url':'https://www.economist.com/interactive/briefing/2022/06/11/huge-foundation-models-are-turbo-charging-ai-progress'
# }])]
if edition_date:
url = 'https://www.economist.com/weeklyedition/' + edition_date