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

Fix #1970040 [The Economist recipe not fetching "Economic & financial indicators" section](https://bugs.launchpad.net/calibre/+bug/1970040)

Browse Source
This commit is contained in:
Kovid Goyal 2022-04-24 10:49:48 +05:30
parent 7752b02a73
commit 6e7fd724fd
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 20 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
recipes/economist.recipe
View File

@ -46,6 +46,13 @@ def process_node(node, html_parent):
html_parent.text = (html_parent.text or '') + text html_parent.text = (html_parent.text or '') + text
def safe_dict(data, *names):
ans = data
for x in names:
ans = ans.get(x) or {}
return ans
def load_article_from_json(raw, root): def load_article_from_json(raw, root):
data = json.loads(raw)['props']['pageProps']['content'] 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(json.dumps(data, indent=2, sort_keys=True))
@ -59,14 +66,14 @@ def load_article_from_json(raw, root):
E(article, 'h1', data['headline'], style='font-size: x-large') E(article, 'h1', data['headline'], style='font-size: x-large')
E(article, 'div', data['description'], style='font-style: italic') E(article, 'div', data['description'], style='font-style: italic')
E(article, 'div', (data['datePublishedString'] or '') + ' | ' + (data['dateline'] or ''), style='color: gray; margin: 1em') E(article, 'div', (data['datePublishedString'] or '') + ' | ' + (data['dateline'] or ''), style='color: gray; margin: 1em')
main_image_url = data.get('image', {}).get('main', {}).get('url', {}).get('canonical') main_image_url = safe_dict(data, 'image', 'main', 'url').get('canonical')
if main_image_url: if main_image_url:
div = E(article, 'div') div = E(article, 'div')
try: try:
E(div, 'img', src=main_image_url) E(div, 'img', src=main_image_url)
except Exception: except Exception:
pass pass
for node in data.get('text', []): for node in data.get('text') or ():
process_node(node, article) process_node(node, article)
@ -235,7 +242,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
# return [('Articles', [{'title':'test', # return [('Articles', [{'title':'test',
# 'url':'https://www.economist.com/briefing/2021/09/11/how-america-wasted-its-unipolar-moment' # 'url':'https://www.economist.com/economic-and-financial-indicators/2022/04/23/economic-data-commodities-and-markets'
# }])] # }])]
if edition_date: if edition_date:
url = 'https://www.economist.com/weeklyedition/' + edition_date url = 'https://www.economist.com/weeklyedition/' + edition_date

13
recipes/economist_free.recipe
View File

@ -46,6 +46,13 @@ def process_node(node, html_parent):
html_parent.text = (html_parent.text or '') + text html_parent.text = (html_parent.text or '') + text
def safe_dict(data, *names):
ans = data
for x in names:
ans = ans.get(x) or {}
return ans
def load_article_from_json(raw, root): def load_article_from_json(raw, root):
data = json.loads(raw)['props']['pageProps']['content'] 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(json.dumps(data, indent=2, sort_keys=True))
@ -59,14 +66,14 @@ def load_article_from_json(raw, root):
E(article, 'h1', data['headline'], style='font-size: x-large') E(article, 'h1', data['headline'], style='font-size: x-large')
E(article, 'div', data['description'], style='font-style: italic') E(article, 'div', data['description'], style='font-style: italic')
E(article, 'div', (data['datePublishedString'] or '') + ' | ' + (data['dateline'] or ''), style='color: gray; margin: 1em') E(article, 'div', (data['datePublishedString'] or '') + ' | ' + (data['dateline'] or ''), style='color: gray; margin: 1em')
main_image_url = data.get('image', {}).get('main', {}).get('url', {}).get('canonical') main_image_url = safe_dict(data, 'image', 'main', 'url').get('canonical')
if main_image_url: if main_image_url:
div = E(article, 'div') div = E(article, 'div')
try: try:
E(div, 'img', src=main_image_url) E(div, 'img', src=main_image_url)
except Exception: except Exception:
pass pass
for node in data.get('text', []): for node in data.get('text') or ():
process_node(node, article) process_node(node, article)
@ -235,7 +242,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
# return [('Articles', [{'title':'test', # return [('Articles', [{'title':'test',
# 'url':'https://www.economist.com/briefing/2021/09/11/how-america-wasted-its-unipolar-moment' # 'url':'https://www.economist.com/economic-and-financial-indicators/2022/04/23/economic-data-commodities-and-markets'
# }])] # }])]
if edition_date: if edition_date:
url = 'https://www.economist.com/weeklyedition/' + edition_date url = 'https://www.economist.com/weeklyedition/' + edition_date