From ba368aba92afcb6be3680ca440640a6fd53332c3 Mon Sep 17 00:00:00 2001 From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com> Date: Fri, 29 Sep 2023 10:36:59 +0530 Subject: [PATCH] Update toiprint.recipe --- recipes/toiprint.recipe | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) diff --git a/recipes/toiprint.recipe b/recipes/toiprint.recipe index 87c14307cf..b2a961cf82 100644 --- a/recipes/toiprint.recipe +++ b/recipes/toiprint.recipe @@ -5,9 +5,9 @@ from datetime import date # default edition is Delhi i.e., 'cap' # Hyderabad - 'toih'; Delhi - 'cap'; Mumbai - 'toim'; Banglore - 'toibgc'; +# Chennai - 'toich'; Chandigarh - 'toicgct'; Jaipur - 'toijc'; Kolkata - 'toikc'; # There are others too, try to figure it out, visit toi epaper link. -# for example, replace 'cap' with 'toih', if you want Hyderabad edition. le = 'cap' # local edition; date0 = date.today().strftime('%Y/%m/%d') @@ -41,6 +41,7 @@ class toiprint(BasicNewsRecipe): .auth { font-size:small; font-weight:bold; color:#202020; } .cap { text-align:center; font-size:small; } img { display:block; margin:0 auto; } + .info { font-size:small; color:#404040; } ''' def get_cover_url(self): @@ -69,14 +70,12 @@ class toiprint(BasicNewsRecipe): for art in sec['Articles']: if 'ArticleName' not in art: continue - link = art['ArticleName'] - page = link.split('_')[-3] - url = page + '/' + link - title = art.get('ArticleTitle', 'unknown') + url = art['ArticleName'] + title = art.get('ArticleTitle', 'unknown').replace('
', '') if art.get('ColumnTitle', '') == '': - desc = 'Page No.' + page + ' | ' + art.get('ArticleBody', '') + desc = 'Page No.' + url.split('_')[-3] + ' | ' + art.get('ArticleBody', '') else: - desc = 'Page No.' + page + ' | ' + art.get('ColumnTitle', '') + desc = 'Page No.' + url.split('_')[-3] + ' | ' + art.get('ColumnTitle', '') self.log('\t', title, '\n\t', desc, '\n\t\t', url) articles.append({'title': title, 'description':desc, 'url': url}) if articles: @@ -89,21 +88,27 @@ class toiprint(BasicNewsRecipe): for x in data: if x['TagName'] == 'ArticleTitle': body += '

' + x['ZoneText'] + '

' - if x['TagName'] == 'ColumnTitle': + elif x['TagName'] == 'ColumnTitle': body += '

' + x['ZoneText'] + '

' - if x['TagName'] == 'Author': + elif x['TagName'] == 'Author': body += '

' + x['ZoneText'].replace('
', '') + '

' - if x['TagName'] in {'ArticleBody', 'Information'}: + elif x['TagName'] in 'ArticleBody': body += x['ZoneText'] - if x['TagName'] in {'LinkTo', 'LinkFrom'}: + elif x['TagName'] in 'Information': + body += '

' + x['ZoneText'] + '

' + elif x['TagName'] in {'LinkTo', 'LinkFrom'}: body += '

' + x['ZoneText'] + '

' - if x['TagName'] == 'Photographs': + elif x['TagName'] == 'Photographs': pag = x['ZoneID'].split('_')[-4] body += '
'.format(img_index + '/Photographs/' + pag + '/' \ + x['ZoneID'] + '.jpg&bucket=andre-toi-out&q=50') - if x['TagName'] == 'ImageCaption': + elif x['TagName'] == 'ImageCaption': body += '
' + x['ZoneText'] + '

' - return '

' + body.replace('
', '

').replace('
', '

') + '

' + elif 'ZoneText' in x: + body += '

' + x['ZoneText'] + '

' + return '
' \ + + body.replace('
', '

').replace('
', '

').replace('<br>', '

').replace('\n', '

') \ + + '
' def print_version(self, url): - return index + '/ArticleZoneJson/' + url + '.json' + return index + '/ArticleZoneJson/' + url.split('_')[-3] + '/' + url + '.json'