fix: handle weird wordpress URLs

dhdaines · Jul 25, 2024 · 8fabc82 · 8fabc82
1 parent 5ca849c
commit 8fabc82
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/.github/workflows/analyse.yml b/.github/workflows/analyse.yml
@@ -52,7 +52,7 @@ jobs:
                 fi
             done
         done
-        alexi -v download -u https://vsadm.ca/citoyens/reglementation/reglementation-durbanisme/index.html -o download/vsadm --all-pdf-links
+        alexi -v download -u https://vsadm.ca/citoyens/reglementation/reglementation-durbanisme/ -o download/vsadm --all-pdf-links
     - name: Extract
       run: |
         alexi -v extract -m download/index.json download/*.pdf

diff --git a/alexi/download.py b/alexi/download.py
@@ -57,6 +57,7 @@ def add_arguments(parser: argparse.ArgumentParser) -> argparse.ArgumentParser:
 def main(args: argparse.Namespace) -> None:
     u = urllib.parse.urlparse(args.url)
     LOGGER.info("Downloading %s", args.url)
+    args.outdir.mkdir(parents=True, exist_ok=True)
     try:
         subprocess.run(
             [
@@ -75,7 +76,10 @@ def main(args: argparse.Namespace) -> None:
             raise
     excludes = [re.compile(r) for r in args.exclude]
     paths = []
-    with open(args.outdir / Path(u.path).name) as infh:
+    index = args.outdir / Path(u.path).name
+    if not index.exists():
+        index = args.outdir / "index.html"
+    with open(index) as infh:
         soup = BeautifulSoup(infh, "lxml")
         if args.all_pdf_links:
             for a in soup.find_all("a"):