Implement recursive page crawling
This commit is contained in:
parent
3d7b72e5ef
commit
9fc2e1af53
5 changed files with 47 additions and 26 deletions
|
|
@ -27,7 +27,7 @@ def build_index():
|
|||
if len(matching_urls) == 0:
|
||||
# if not url.strip() in dictionary[word]:
|
||||
entries = dictionary[word]
|
||||
entry = {"url": url.strip(), "count": 1}
|
||||
entry = {"url": url.strip(), "count": 1, "filename": str(path)}
|
||||
dictionary[word].append(entry)
|
||||
else:
|
||||
entries = dictionary[word]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue