mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge branch 'master' of https://github.com/unkn0w7n/calibre
This commit is contained in:
commit
f3420c6b15
@ -1,3 +1,5 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
import json
|
||||
import re
|
||||
from collections import OrderedDict
|
||||
@ -7,8 +9,6 @@ from calibre import browser, random_user_agent
|
||||
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
||||
from mechanize import Request
|
||||
|
||||
_issue_url = "" # custom issue url
|
||||
|
||||
|
||||
class HBR(BasicNewsRecipe):
|
||||
title = "Harvard Business Review"
|
||||
@ -129,15 +129,23 @@ class HBR(BasicNewsRecipe):
|
||||
content_ele.append(new_soup.body)
|
||||
return str(soup)
|
||||
|
||||
recipe_specific_options = {
|
||||
'issue': {
|
||||
'short': 'Enter the Issue Number you want to download ',
|
||||
'long': 'For example, 2403'
|
||||
}
|
||||
}
|
||||
|
||||
def parse_index(self):
|
||||
if not _issue_url:
|
||||
d = self.recipe_specific_options.get('issue')
|
||||
if not (d and isinstance(d, str)):
|
||||
soup = self.index_to_soup(f"{self.base_url}/magazine")
|
||||
a = soup.find("a", href=lambda x: x and x.startswith("/archive-toc/"))
|
||||
cov_url = a.find("img", attrs={"src": True})["src"]
|
||||
self.cover_url = urljoin(self.base_url, cov_url)
|
||||
issue_url = urljoin(self.base_url, a["href"])
|
||||
else:
|
||||
issue_url = _issue_url
|
||||
issue_url = 'https://hbr.org/archive-toc/BR' + d
|
||||
mobj = re.search(r"archive-toc/(?P<issue>(BR)?\d+)\b", issue_url)
|
||||
if mobj:
|
||||
self.cover_url = f'https://hbr.org/resources/images/covers/{mobj.group("issue")}_500.png'
|
||||
|
@ -20,7 +20,23 @@ class OpenMagazine(BasicNewsRecipe):
|
||||
'blockquote{color:#404040;}'
|
||||
'.about-author{font-size:small;}'
|
||||
|
||||
recipe_specific_options = {
|
||||
'days': {
|
||||
'short': 'Oldest article to download from this news source. In days ',
|
||||
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
||||
'default': str(oldest_article)
|
||||
}
|
||||
}
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
||||
d = self.recipe_specific_options.get('days')
|
||||
if d and isinstance(d, str):
|
||||
self.oldest_article = float(d)
|
||||
|
||||
def get_cover_url(self):
|
||||
d = self.recipe_specific_options.get('days')
|
||||
if not (d and isinstance(d, str)):
|
||||
soup = self.index_to_soup('https://openthemagazine.com/')
|
||||
tag = soup.find(attrs={'class': 'magazine-item mr-1'})
|
||||
if tag:
|
||||
|
@ -20,7 +20,8 @@ class Reuters(BasicNewsRecipe):
|
||||
'reaching billions of people worldwide every day. Reuters provides business, financial, national and international '
|
||||
'news to professionals via desktop terminals, the world’s media organizations, industry events and directly to consumers.'
|
||||
)
|
||||
masthead_url = 'https://www.reutersprofessional.com/wp-content/uploads/2024/03/primary-logo.svg'
|
||||
masthead_url = 'https://www.reutersagency.com/wp-content/uploads/2024/06/reuters-logo.png'
|
||||
cover_url = 'https://yt3.googleusercontent.com/ytc/AIdro_mk43b9eQwN15ZBDyMPDaElxvw4V-oUS9XDUvVnYB3gA9yA=s1024'
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
oldest_article = 1.2 # days
|
||||
|
@ -1,3 +1,5 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
from collections import OrderedDict
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
||||
@ -25,6 +27,13 @@ class Sportstar(BasicNewsRecipe):
|
||||
.author, .publish-time {font-size:small;}
|
||||
'''
|
||||
|
||||
recipe_specific_options = {
|
||||
'issue': {
|
||||
'short': 'Enter the Issue Number you want to download\n(Volume-Issue format)',
|
||||
'long': 'For example, 47-16'
|
||||
}
|
||||
}
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1', attrs={'class':'title'}),
|
||||
dict(name='h2', attrs={'class':'sub-title'}),
|
||||
@ -39,10 +48,15 @@ class Sportstar(BasicNewsRecipe):
|
||||
]
|
||||
|
||||
def parse_index(self):
|
||||
d = self.recipe_specific_options.get('issue')
|
||||
if d and isinstance(d, str):
|
||||
issue_url = 'https://sportstar.thehindu.com/magazine/issue/vol' + d
|
||||
else:
|
||||
soup = self.index_to_soup('https://sportstar.thehindu.com/magazine/')
|
||||
url = soup.find('a', href=lambda x: x and x.startswith('https://sportstar.thehindu.com/magazine/issue/'))['href']
|
||||
self.log('Downloading Issue: ', url)
|
||||
soup = self.index_to_soup(url)
|
||||
issue_url = soup.find('a', href=lambda x: x and x.startswith('https://sportstar.thehindu.com/magazine/issue/'))['href']
|
||||
self.log('Downloading Issue: ', issue_url)
|
||||
|
||||
soup = self.index_to_soup(issue_url)
|
||||
|
||||
feeds = OrderedDict()
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user