Garmelon/wikilyze
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Handle revisions without text

Browse source
This commit is contained in:
Joscha 2022-09-30 01:34:06 +02:00
parent 1db581725b
commit 7cf5b013da
1 changed files with 3 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

9
sift/sift.py
View file

@ -20,17 +20,14 @@ def process_page(page):
info["redirect"] = page.redirect info["redirect"] = page.redirect
else: else:
[revision] = list(page) # Every page has exactly one revision [revision] = list(page) # Every page has exactly one revision
if revision.text is not None:
info["length"] = len(revision.text)
length = len(revision.text)
info["length"] = length
# Parsing may fail for articles with length 0
if length > 0:
links = [] links = []
for link in wtp.parse(revision.text).wikilinks: for link in wtp.parse(revision.text).wikilinks:
start, end = link.span start, end = link.span
links.append((link.title, start, end)) links.append((link.title, start, end))
info["links"] = links info["links"] = links
print(json.dumps(info, check_circular=False, separators=(",", ":"))) print(json.dumps(info, check_circular=False, separators=(",", ":")))