mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 17:41:15 +00:00
54a6db1c2c
The connector can process a Wikipedia page and output the HTML, the plain text contents, and the summary. No API key required Also add test case verifying that 3 files are indeed created (one for HTML, one for text, one for the summary).
17 lines
469 B
Bash
Executable File
17 lines
469 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
--wikipedia-page-title "Open Source Software" \
|
|
--structured-output-dir wikipedia-ingest-output \
|
|
--num-processes 2 \
|
|
--verbose
|
|
|
|
if [ "$(find 'wikipedia-ingest-output' -type f -printf '.' | wc -c)" != 3 ]; then
|
|
echo
|
|
echo "3 files should have been created."
|
|
exit 1
|
|
fi
|