Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -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 2023-11-11 11:48:50 +05:30
commit d266fe5447
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
5 changed files with 33 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
recipes/natgeo.recipe
View File

@ -135,6 +135,11 @@ class NatGeo(BasicNewsRecipe):
.auth, .time { font-size:small; color:#5c5c5c; }
'''
def get_cover_url(self):
soup = self.index_to_soup('https://www.nationalgeographic.com/magazine/')
png = re.findall('https://i\.natgeofe\.com\S+?national-geographic-\S+?\.jpg', soup.decode('utf-8'))
return png[0] + '?w=1000&h=1000'
def parse_index(self):
pages = [
'https://www.nationalgeographic.com/animals',
@ -176,3 +181,9 @@ class NatGeo(BasicNewsRecipe):
# for high res images use '?w=2000&h=2000'
img['src'] = img['src'] + '?w=1000&h=1000'
return soup
def populate_article_metadata(self, article, soup, first):
summ = soup.find(attrs={'class':'byline'})
if summ:
article.summary = self.tag_to_string(summ)
article.text_summary = self.tag_to_string(summ)

6
recipes/natgeohis.recipe
View File

@ -160,3 +160,9 @@ class NatGeo(BasicNewsRecipe):
# for high res images use '?w=2000&h=2000'
img['src'] = img['src'] + '?w=1000&h=1000'
return soup
def populate_article_metadata(self, article, soup, first):
summ = soup.find(attrs={'class':'byline'})
if summ:
article.summary = self.tag_to_string(summ)
article.text_summary = self.tag_to_string(summ)

8
recipes/natgeomag.recipe
View File

@ -143,7 +143,7 @@ class NatGeo(BasicNewsRecipe):
self.log('Downloading ', url)
self.timefmt = ' [' + edition + ']'
soup = self.index_to_soup(url)
png = re.findall('https://i\.natgeofe\.com\S+?national-geographic-magazine-\S+?\.jpg', soup.decode('utf-8'))
png = re.findall('https://i\.natgeofe\.com\S+?national-geographic-\S+?\.jpg', soup.decode('utf-8'))
self.cover_url = png[0] + '?w=1000&h=1000'
name = soup.find(attrs={'class':lambda x: x and 'Header__Description' in x.split()})
@ -179,3 +179,9 @@ class NatGeo(BasicNewsRecipe):
# for high res images use '?w=2000&h=2000'
img['src'] = img['src'] + '?w=1200&h=1200'
return soup
def populate_article_metadata(self, article, soup, first):
summ = soup.find(attrs={'class':'byline'})
if summ:
article.summary = self.tag_to_string(summ)
article.text_summary = self.tag_to_string(summ)

4
recipes/theeconomictimes_india_print_edition.recipe
View File

@ -58,6 +58,10 @@ class TheEconomicTimes(BasicNewsRecipe):
]
def parse_index(self):
self.log(
'\n***\nif this recipe fails, report it on: '
'https://www.mobileread.com/forums/forumdisplay.php?f=228\n***\n'
)
soup = self.index_to_soup(
'https://economictimes.indiatimes.com/print_edition.cms'
)

6
recipes/toiprint.recipe
View File

@ -52,6 +52,10 @@ class toiprint(BasicNewsRecipe):
return cover
def parse_index(self):
self.log(
'\n***\nif this recipe fails, report it on: '
'https://www.mobileread.com/forums/forumdisplay.php?f=228\n***\n'
)
url = index + '/DayIndex/' + date_ + '_' + le + '.json'
raw = self.index_to_soup(url, raw=True)
data = json.loads(raw)
@ -73,7 +77,7 @@ class toiprint(BasicNewsRecipe):
if 'ArticleName' not in art:
continue
url = art['ArticleName']
title = art.get('ArticleTitle', 'unknown').replace('<br>', '')
title = art.get('ArticleTitle', 'unknown').replace('<br>', '').replace('<br/>', '')
if art.get('ColumnTitle', '') == '':
desc = 'Page No.' + url.split('_')[-3] + ' | ' + art.get('ArticleBody', '')
else: