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

...

Browse Source 
caravan, foreign affairs, frontline
This commit is contained in:
unkn0w7n 2024-07-23 11:51:43 +05:30
parent 9e0bf731d3
commit 402b952f4d
3 changed files with 41 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
recipes/caravan_magazine.recipe
View File

@ -1,3 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
import json
from urllib.parse import quote, urlparse
@ -118,6 +120,13 @@ class CaravanMagazine(BasicNewsRecipe):
return br
return br
recipe_specific_options = {
'date': {
'short': 'The date of the edition to download (MM-YYYY format)',
'long': 'For example, 07-2024'
}
}
def parse_index(self):
self.log(
'\n***\nif this recipe fails, report it on: '
@ -125,9 +134,11 @@ class CaravanMagazine(BasicNewsRecipe):
)
api = 'https://api.caravanmagazine.in/api/trpc/magazines.getLatestIssue'
# for past editions
# inp = json.dumps({"0":{"json":{"month":6,"year":2023}}})
# api = 'https://api.caravanmagazine.in/api/trpc/magazines.getForMonthAndYear?batch=1&input=' + quote(inp, safe='')
d = self.recipe_specific_options.get('date')
if d and isinstance(d, str):
x = d.split('-')
inp = json.dumps({"0":{"json":{"month":int(x[0]),"year":int(x[1])}}})
api = 'https://api.caravanmagazine.in/api/trpc/magazines.getForMonthAndYear?batch=1&input=' + quote(inp, safe='')
raw = json.loads(self.index_to_soup(api, raw=True))
if isinstance(raw, list):

11
recipes/foreignaffairs.recipe
View File

@ -127,6 +127,13 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
INDEX = 'https://www.foreignaffairs.com/magazine'
recipe_specific_options = {
'issue': {
'short': 'Enter the Issue Number you want to download ',
'long': 'For example, 2024/103/1'
}
}
keep_only_tags = [
classes('article-header article-body article-lead-image article-body-text'),
]
@ -140,6 +147,10 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
remove_empty_feeds = True
def parse_index(self):
d = self.recipe_specific_options.get('issue')
if d and isinstance(d, str):
self.INDEX = 'https://www.foreignaffairs.com/issues/' + d
soup = self.index_to_soup(self.INDEX)
# get dates
date = re.split(r'\s\|\s', self.tag_to_string(

18
recipes/frontline.recipe
View File

@ -1,3 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe, classes
@ -53,8 +55,20 @@ class Frontline(BasicNewsRecipe):
src.extract()
return soup
recipe_specific_options = {
'issue': {
'short': 'Enter the Issue Number you want to download\n(Volume-Issue format)',
'long': 'For example, 41-12'
}
}
def parse_index(self):
soup = self.index_to_soup('https://frontline.thehindu.com/current-issue/')
issue_url = 'https://frontline.thehindu.com/current-issue/'
d = self.recipe_specific_options.get('issue')
if d and isinstance(d, str):
issue_url = 'https://frontline.thehindu.com/magazine/issue/vol' + d
soup = self.index_to_soup(issue_url)
if cover := soup.find('div', attrs={'class':'magazine'}):
self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('_320', '_1200')
@ -82,4 +96,4 @@ class Frontline(BasicNewsRecipe):
continue
self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url)
feeds_dict[section].append({"title": title, "url": url, "description": desc})
return [(section, articles) for section, articles in feeds_dict.items()]
return [(section, articles) for section, articles in feeds_dict.items()]