Update tls_mag.recipe

reduce file size
This commit is contained in:
unkn0w7n 2024-09-29 20:21:32 +05:30
parent 682624e573
commit 1b91defced

View File

@ -19,7 +19,7 @@ def get_id(url):
return re.search('\?p=(\S+)>', str(rq.info())).group(1) return re.search('\?p=(\S+)>', str(rq.info())).group(1)
class tls(BasicNewsRecipe): class TLS(BasicNewsRecipe):
title = 'Times Literary Supplement' title = 'Times Literary Supplement'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
description = ( description = (
@ -39,7 +39,7 @@ class tls(BasicNewsRecipe):
.desc { font-style:italic; color:#202020; } .desc { font-style:italic; color:#202020; }
.auth { font-size:small; } .auth { font-size:small; }
em, blockquote { color:#202020; } em, blockquote { color:#202020; }
.det { font-size:small; color:#202020; font-weight:bold; } .det { font-size:small; color:#202020; }
''' '''
recipe_specific_options = { recipe_specific_options = {
@ -60,7 +60,7 @@ class tls(BasicNewsRecipe):
url = 'https://www.the-tls.co.uk/wp-json/tls/v2/contents-page/' + get_id(issue) url = 'https://www.the-tls.co.uk/wp-json/tls/v2/contents-page/' + get_id(issue)
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
data = json.loads(raw) data = json.loads(raw)
self.cover_url = data['featuredimage']['full_image'] + '?w600' self.cover_url = data['featuredimage']['full_image'].split('?')[0] + '?w600'
self.timefmt = ' [' + data['issuedateline']['issuedate'] + ']' self.timefmt = ' [' + data['issuedateline']['issuedate'] + ']'
if data['issuedateline']['issuenumber']: if data['issuedateline']['issuenumber']:
self.description = 'Issue ' + data['issuedateline']['issuenumber'] self.description = 'Issue ' + data['issuedateline']['issuenumber']
@ -93,6 +93,11 @@ class tls(BasicNewsRecipe):
self.log(' ', title, '\n\t', desc, '\n\t', url) self.log(' ', title, '\n\t', desc, '\n\t', url)
return ({ 'title': title, 'description': desc, 'url': url }) return ({ 'title': title, 'description': desc, 'url': url })
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src':True}):
img['src'] = img['src'].split('?')[0] + '?w=600'
return soup
def preprocess_raw_html(self, raw, *a): def preprocess_raw_html(self, raw, *a):
pg = re.search(r'var tlsPageObject = ({.+)', raw).group(1) pg = re.search(r'var tlsPageObject = ({.+)', raw).group(1)
data = json.JSONDecoder().raw_decode(pg)[0] data = json.JSONDecoder().raw_decode(pg)[0]