- .gitignore +2 -1
- API/app.py +1 -0
- Client/clear_db.py +10 -0
- Client/hunt.py +24 -4
.gitignore
CHANGED
|
@@ -1,3 +1,4 @@
|
|
| 1 |
.env
|
| 2 |
*.txt
|
| 3 |
-
db
|
|
|
|
|
|
| 1 |
.env
|
| 2 |
*.txt
|
| 3 |
+
db
|
| 4 |
+
images
|
API/app.py
CHANGED
|
@@ -244,6 +244,7 @@ async def download(
|
|
| 244 |
zipf.write(f"Stash/{post_id}.png", post_id + ".png")
|
| 245 |
|
| 246 |
return FileResponse(path=f"Stash/{timezip}.zip", media_type="application/zip", filename=f"{timezip}.zip")
|
|
|
|
| 247 |
@app.get("/")
|
| 248 |
async def read_root():
|
| 249 |
return {"message": "Hello, World!"}
|
|
|
|
| 244 |
zipf.write(f"Stash/{post_id}.png", post_id + ".png")
|
| 245 |
|
| 246 |
return FileResponse(path=f"Stash/{timezip}.zip", media_type="application/zip", filename=f"{timezip}.zip")
|
| 247 |
+
|
| 248 |
@app.get("/")
|
| 249 |
async def read_root():
|
| 250 |
return {"message": "Hello, World!"}
|
Client/clear_db.py
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
import shutil
|
| 3 |
+
|
| 4 |
+
os.chdir(os.path.dirname(os.path.abspath(__file__)))
|
| 5 |
+
|
| 6 |
+
shutil.rmtree("images", ignore_errors=True)
|
| 7 |
+
shutil.rmtree("db", ignore_errors=True)
|
| 8 |
+
for file in os.listdir():
|
| 9 |
+
if file.endswith(".txt"):
|
| 10 |
+
os.remove(file)
|
Client/hunt.py
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
import os
|
| 2 |
import lmdb
|
| 3 |
import requests
|
|
|
|
|
|
|
| 4 |
|
| 5 |
img_base = 'https://i.pximg.net/img-original/'
|
| 6 |
|
|
@@ -29,6 +31,9 @@ with db.begin(write=True) as txn:
|
|
| 29 |
for index in indexs:
|
| 30 |
group_name = valid[index].rsplit(".", 1)[0]
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
with open(valid[index], "r") as f:
|
| 33 |
post_ids = [x for x in f.read().split("\n") if x]
|
| 34 |
|
|
@@ -42,7 +47,22 @@ with db.begin(write=True) as txn:
|
|
| 42 |
for post_id in missing_post_ids:
|
| 43 |
txn.put(post_id.encode(), b'\x00')
|
| 44 |
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
import lmdb
|
| 3 |
import requests
|
| 4 |
+
import io
|
| 5 |
+
from zipfile import ZipFile
|
| 6 |
|
| 7 |
img_base = 'https://i.pximg.net/img-original/'
|
| 8 |
|
|
|
|
| 31 |
for index in indexs:
|
| 32 |
group_name = valid[index].rsplit(".", 1)[0]
|
| 33 |
|
| 34 |
+
os.makedirs(f"images/{group_name}", exist_ok=True)
|
| 35 |
+
group_cache = os.listdir(f"images/{group_name}")
|
| 36 |
+
|
| 37 |
with open(valid[index], "r") as f:
|
| 38 |
post_ids = [x for x in f.read().split("\n") if x]
|
| 39 |
|
|
|
|
| 47 |
for post_id in missing_post_ids:
|
| 48 |
txn.put(post_id.encode(), b'\x00')
|
| 49 |
|
| 50 |
+
to_download = {}
|
| 51 |
+
for post_id in set(post_ids):
|
| 52 |
+
if f"{post_id}.png" in images_cache:
|
| 53 |
+
continue
|
| 54 |
+
url = txn.get(post_id.encode())
|
| 55 |
+
if url != b'\x00':
|
| 56 |
+
to_download[post_id] = url.decode()
|
| 57 |
+
|
| 58 |
+
images_zip = requests.post('https://q6-p.hf.space/download', json={'posts': data})
|
| 59 |
+
|
| 60 |
+
with io.BytesIO(images_zip.content) as f:
|
| 61 |
+
with ZipFile(f) as z:
|
| 62 |
+
z.extractall("images/Stash")
|
| 63 |
+
|
| 64 |
+
for i, post_id in enumerate(post_ids):
|
| 65 |
+
print(post_id)
|
| 66 |
+
if f"{post_id}.png" in images_cache and f"{i}_{post_id}.png" not in group_cache:
|
| 67 |
+
os.link(f"images/Stash/{post_id}.png", f"images/{group_name}/{i}_{post_id}.png")
|
| 68 |
+
continue
|