prabhaavp/datamining_881
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

small changes

Browse Source
This commit is contained in:
IshaAtteri
2026-03-12 12:16:51 -04:00
parent a1beba6730
commit 437492e623
1 changed files with 0 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
scripts/scrape.py
View File

@@ -52,7 +52,6 @@ def extract_movie_info(file_path):
directed_by = data.get_text(" ", strip=True) directed_by = data.get_text(" ", strip=True)
elif header_text == "Starring": elif header_text == "Starring":
# Get cast members split by <br> or links/text
cast_items = list(data.stripped_strings) cast_items = list(data.stripped_strings)
cast = cast_items[:5] cast = cast_items[:5]
@@ -64,11 +63,9 @@ def extract_movie_info(file_path):
plot_header = soup.find(id="Plot") plot_header = soup.find(id="Plot")
if plot_header: if plot_header:
# Move to the parent heading container if needed
current = plot_header.parent current = plot_header.parent
for sibling in current.find_next_siblings(): for sibling in current.find_next_siblings():
# Stop when next h2 section begins
if sibling.name == "div" and "mw-heading2" in sibling.get("class", []): if sibling.name == "div" and "mw-heading2" in sibling.get("class", []):
break break
if sibling.name == "p": if sibling.name == "p":