1
0
Fork 0
mirror of https://github.com/kemayo/leech synced 2025-12-06 00:15:22 +01:00

Compare commits

...

2 commits

Author SHA1 Message Date
Kevin Pedro
de6913a9af simplify algorithm 2025-03-08 09:48:32 -06:00
Kevin Pedro
d4e1214be3 return to loop-based algorithm 2025-03-08 09:40:42 -06:00

View file

@ -76,15 +76,24 @@ class Arbitrary(Site):
else:
# set of already processed urls. Stored to detect loops.
found_content_urls = set()
content_url = definition.url
content_urls = [definition.url]
def process_content_url(content_url):
if content_url in found_content_urls:
return False
return None
found_content_urls.add(content_url)
for chapter in self._chapter(content_url, definition):
story.add(chapter)
if definition.next_selector:
return content_url
while content_urls:
for temp_url in content_urls:
# stop inner loop once a new link is found
if content_url := process_content_url(temp_url):
break
# reset url list
content_urls = []
if content_url and definition.next_selector:
soup, base = self._soup(content_url)
next_link = soup.select(definition.next_selector)
if next_link:
@ -92,14 +101,7 @@ class Arbitrary(Site):
next_link_url = str(next_link_item.get('href'))
if base:
next_link_url = self._join_url(base, next_link_url)
content_url = self._join_url(content_url, next_link_url)
# stop loop once a new link is found
status = process_content_url(content_url)
if status:
break
return True
process_content_url(content_url)
content_urls.append(self._join_url(content_url, next_link_url))
if not story:
raise SiteException("No story content found; check the content selectors")