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

Update hindu_business_line_print_edition.recipe

Browse Source 
looks like BL doesn't load all articles without adding date to the link.
This commit is contained in:
unkn0w7n 2023-06-20 17:05:00 +05:30
parent eec2b8e929
commit 5b42712302
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/hindu_business_line_print_edition.recipe
View File

@ -39,7 +39,7 @@ class BusinessLine(BasicNewsRecipe):
] ]
remove_tags = [ remove_tags = [
classes('hide-mobile comments-shares share-page editiondetails') classes('hide-mobile comments-shares share-page editiondetails author-img')
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
@ -50,13 +50,13 @@ class BusinessLine(BasicNewsRecipe):
return soup return soup
def parse_index(self): def parse_index(self):
dt = date.today().strftime('%Y-%m-%d')
# For past editions, set date to, for example, '2023-01-28'
# dt = '2023-01-28'
if local_edition: if local_edition:
yr = str(date.today().year) url = absurl('/todays-paper/' + dt + '/' + local_edition + '/')
mn = date.today().strftime('%m')
dy = date.today().strftime('%d')
url = absurl('/todays-paper/' + yr + '-' + mn + '-' + dy + '/' + local_edition + '/')
else: else:
url = 'https://www.thehindubusinessline.com/todays-paper/' url = absurl('/todays-paper/' + dt + '/bl_chennai/')
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
soup = self.index_to_soup(raw) soup = self.index_to_soup(raw)
ans = self.hindu_parse_index(soup) ans = self.hindu_parse_index(soup)
@ -74,8 +74,8 @@ class BusinessLine(BasicNewsRecipe):
if not self.tag_to_string(script).strip().startswith('let grouped_articles = {}'): if not self.tag_to_string(script).strip().startswith('let grouped_articles = {}'):
continue continue
if script is not None: if script is not None:
art = re.search(r'grouped_articles = ({\"[^<]+?]})', self.tag_to_string(script)) art = re.search(r'grouped_articles = ({\".*)', self.tag_to_string(script))
data = json.loads(art.group(1)) data = json.JSONDecoder().raw_decode(art.group(1))[0]
feeds_dict = defaultdict(list) feeds_dict = defaultdict(list)