public-mirrors/NewsBlur-viq
1
0
Fork 0
mirror of https://github.com/viq/NewsBlur.git synced 2025-09-18 21:43:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Upgrading readability 0.3.0.5.

Browse source
This commit is contained in:
Samuel Clay 2014-09-29 11:22:22 -07:00
parent 2ce9ad8f9c
commit 6d69401887
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
vendor/readability/readability.py vendored
View file

@ -160,6 +160,7 @@ class Document:
self.remove_unlikely_candidates()
self.transform_misused_divs_into_paragraphs()
candidates = self.score_paragraphs()
best_candidate = self.select_best_candidate(candidates)
if best_candidate:
@ -273,7 +274,7 @@ class Document:
self.TEXT_LENGTH_THRESHOLD)
candidates = {}
ordered = []
for elem in self.tags(self._html(), "p", "pre", "td", "section", "article"):
for elem in self.tags(self._html(), "p", "pre", "td"):
parent_node = elem.getparent()
if parent_node is None:
continue
@ -451,6 +452,7 @@ class Document:
for kind in ['p', 'img', 'li', 'a', 'embed', 'input']:
counts[kind] = len(el.findall('.//%s' % kind))
counts["li"] -= 100
counts["input"] -= len(el.findall('.//input[@type="hidden"]'))
# Count the text length excluding any surrounding whitespace
content_length = text_length(el)