aboutsummaryrefslogtreecommitdiffstats
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md11
1 files changed, 11 insertions, 0 deletions
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..486bdb0
--- /dev/null
+++ b/README.md
@@ -0,0 +1,11 @@
+Scraper to collect and resize kpop images for a captcha. Made for 4get
+
+1. Downloads images accoding to groups specified in `PULL_GROUPS` in `groups.py`
+2. Renames images to numberd `[x].png`
+3. Uses insightface's `buffalo_1` face detection to crop a 100x100 area around faces in downloaded image
+
+Configure `groups.py` accordingly before running
+```
+uv sync
+uv scrape_data.py
+```
send patches to the email below
yukais@pinapelz.com
include the subject [PATCH repo_name]
pinapelz.com
homepage