Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update hbr.recipe

Browse Source
This commit is contained in:
unkn0w7n 2024-07-27 13:21:43 +05:30
parent 3fe8bfd89a
commit 2025f05a1b
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/hbr.recipe
View File

@ -1,3 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
import json import json
import re import re
from collections import OrderedDict from collections import OrderedDict
@ -7,8 +9,6 @@ from calibre import browser, random_user_agent
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
from mechanize import Request from mechanize import Request
_issue_url = "" # custom issue url
class HBR(BasicNewsRecipe): class HBR(BasicNewsRecipe):
title = "Harvard Business Review" title = "Harvard Business Review"
@ -129,15 +129,23 @@ class HBR(BasicNewsRecipe):
content_ele.append(new_soup.body) content_ele.append(new_soup.body)
return str(soup) return str(soup)
recipe_specific_options = {
'issue': {
'short': 'Enter the Issue Number you want to download ',
'long': 'For example, 2403'
}
}
def parse_index(self): 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") soup = self.index_to_soup(f"{self.base_url}/magazine")
a = soup.find("a", href=lambda x: x and x.startswith("/archive-toc/")) a = soup.find("a", href=lambda x: x and x.startswith("/archive-toc/"))
cov_url = a.find("img", attrs={"src": True})["src"] cov_url = a.find("img", attrs={"src": True})["src"]
self.cover_url = urljoin(self.base_url, cov_url) self.cover_url = urljoin(self.base_url, cov_url)
issue_url = urljoin(self.base_url, a["href"]) issue_url = urljoin(self.base_url, a["href"])
else: 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) mobj = re.search(r"archive-toc/(?P<issue>(BR)?\d+)\b", issue_url)
if mobj: if mobj:
self.cover_url = f'https://hbr.org/resources/images/covers/{mobj.group("issue")}_500.png' self.cover_url = f'https://hbr.org/resources/images/covers/{mobj.group("issue")}_500.png'