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 NatGeo

Browse Source
This commit is contained in:
unkn0w7n 2024-05-04 12:15:32 +05:30
parent af0433edb3
commit 8e93f979f5
3 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/natgeo.recipe
View File

@ -106,7 +106,7 @@ def parse_article(edg):
yield '<h1>' + escape(sc['sclTtl']) + '</h1>' yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>' yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
yield '<p>' yield '<p>'
for line in parse_contributors(edg['cntrbGrp']): for line in parse_contributors(edg.get('cntrbGrp', {})):
yield line yield line
ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y') ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
yield '<div class="time">Published: ' + escape(ts) + '</div>' yield '<div class="time">Published: ' + escape(ts) + '</div>'

2
recipes/natgeohis.recipe
View File

@ -105,7 +105,7 @@ def parse_article(edg):
yield '<h1>' + escape(sc['sclTtl']) + '</h1>' yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>' yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
yield '<p>' yield '<p>'
for line in parse_contributors(edg['cntrbGrp']): for line in parse_contributors(edg.get('cntrbGrp', {})):
yield line yield line
ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y') ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
yield '<div class="time">Published: ' + escape(ts) + '</div>' yield '<div class="time">Published: ' + escape(ts) + '</div>'

16
recipes/natgeomag.recipe
View File

@ -110,7 +110,7 @@ def parse_article(edg):
yield '<h1>' + escape(sc['sclTtl']) + '</h1>' yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>' yield '<div class="byline">' + escape(sc['sclDsc']) + '</div>'
yield '<p>' yield '<p>'
for line in parse_contributors(edg['cntrbGrp']): for line in parse_contributors(edg.get('cntrbGrp', {})):
yield line yield line
ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y') ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
yield '<div class="time">Published: ' + escape(ts) + '</div>' yield '<div class="time">Published: ' + escape(ts) + '</div>'
@ -187,14 +187,20 @@ class NatGeo(BasicNewsRecipe):
name = soup.find(attrs={'class':lambda x: x and 'Header__Description' in x.split()}) name = soup.find(attrs={'class':lambda x: x and 'Header__Description' in x.split()})
self.title = 'National Geographic ' + self.tag_to_string(name) self.title = 'National Geographic ' + self.tag_to_string(name)
ans = {} ans = {}
ans2 = None
if photoart := soup.find(attrs={'class':lambda x: x and 'BgImagePromo__Container__Text__Link' in x.split()}): if photoart := soup.find(attrs={'class':lambda x: x and 'BgImagePromo__Container__Text__Link' in x.split()}):
ans2 = [] section = 'Photo Essay'
title = self.tag_to_string(photoart) title = self.tag_to_string(photoart)
url = photoart['href'] url = photoart['href']
if url.startswith('/'): if url.startswith('/'):
url = 'https://www.nationalgeographic.com' + url url = 'https://www.nationalgeographic.com' + url
ans2.append(('Photo Essay', [{'title': title, 'url': url}])) articles = ans.setdefault(section, [])
articles.append({'title': title, 'url': url})
for promo in soup.findAll(**classes('OneUpPromoCard__Content')):
url = promo.a['href']
section = self.tag_to_string(promo.find(**classes('SectionLabel')))
title = self.tag_to_string(promo.find(**classes('Card__Content__Heading')))
articles = ans.setdefault(section, [])
articles.append({'title': title, 'url': url})
for gird in soup.findAll(attrs={'class':'GridPromoTile'}): for gird in soup.findAll(attrs={'class':'GridPromoTile'}):
for article in soup.findAll('article'): for article in soup.findAll('article'):
a = article.find('a') a = article.find('a')
@ -208,8 +214,6 @@ class NatGeo(BasicNewsRecipe):
articles = ans.setdefault(section, []) articles = ans.setdefault(section, [])
articles.append({'title': title, 'url': url}) articles.append({'title': title, 'url': url})
self.log(pformat(ans)) self.log(pformat(ans))
if ans2:
return list(ans.items()) + ans2
return list(ans.items()) return list(ans.items())
def preprocess_raw_html(self, raw_html, url): def preprocess_raw_html(self, raw_html, url):