Moved transactions
Browse files- Client/Extract Pixiv/ai_search.py +1 -1
- Client/hunt.py +18 -18
- Client/test2.py +15 -0
Client/Extract Pixiv/ai_search.py
CHANGED
|
@@ -11,7 +11,7 @@ os.chdir(os.path.dirname(os.path.abspath(__file__)))
|
|
| 11 |
|
| 12 |
input_url = input("Enter the URL: ")
|
| 13 |
|
| 14 |
-
pages =
|
| 15 |
|
| 16 |
params = {
|
| 17 |
'raw': input_url,
|
|
|
|
| 11 |
|
| 12 |
input_url = input("Enter the URL: ")
|
| 13 |
|
| 14 |
+
pages = 120 // 60
|
| 15 |
|
| 16 |
params = {
|
| 17 |
'raw': input_url,
|
Client/hunt.py
CHANGED
|
@@ -27,17 +27,17 @@ for inp in inputs:
|
|
| 27 |
start, end = map(int, inp.split("-"))
|
| 28 |
indexs.extend(range(start - 1, end))
|
| 29 |
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
group_name = valid[index].rsplit(".", 1)[0]
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
-
filtered_post_ids = [post_id for post_id in post_ids if not txn.get(post_id.encode())]
|
| 40 |
-
print(filtered_post_ids)
|
| 41 |
data = requests.post('https://q6-p.hf.space/pixif', json={"post_ids": filtered_post_ids}).json()
|
| 42 |
|
| 43 |
for post_id, url in data.items():
|
|
@@ -46,7 +46,7 @@ with db.begin(write=True) as txn:
|
|
| 46 |
missing_post_ids = set(filtered_post_ids) - set(data.keys())
|
| 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:
|
|
@@ -55,14 +55,14 @@ with db.begin(write=True) as txn:
|
|
| 55 |
if url != b'\x00':
|
| 56 |
to_download[post_id] = url.decode()
|
| 57 |
|
| 58 |
-
|
| 59 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
|
|
|
| 27 |
start, end = map(int, inp.split("-"))
|
| 28 |
indexs.extend(range(start - 1, end))
|
| 29 |
|
| 30 |
+
for index in indexs:
|
| 31 |
+
group_name = valid[index].rsplit(".", 1)[0]
|
|
|
|
| 32 |
|
| 33 |
+
group_cache = os.listdir(f"images/{group_name}")
|
| 34 |
|
| 35 |
+
with open(valid[index], "r") as f:
|
| 36 |
+
post_ids = [x for x in f.read().split("\n") if x]
|
| 37 |
+
|
| 38 |
+
with db.begin(write=True) as txn:
|
| 39 |
+
filtered_post_ids = [post_id for post_id in post_ids if txn.get(post_id.encode()) == None]
|
| 40 |
|
|
|
|
|
|
|
| 41 |
data = requests.post('https://q6-p.hf.space/pixif', json={"post_ids": filtered_post_ids}).json()
|
| 42 |
|
| 43 |
for post_id, url in data.items():
|
|
|
|
| 46 |
missing_post_ids = set(filtered_post_ids) - set(data.keys())
|
| 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:
|
|
|
|
| 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 |
+
if f"{post_id}.png" in images_cache and f"{i}_{post_id}.png" not in group_cache:
|
| 66 |
+
os.makedirs(f"images/{group_name}", exist_ok=True)
|
| 67 |
+
os.link(f"images/Stash/{post_id}.png", f"images/{group_name}/{i}_{post_id}.png")
|
| 68 |
+
continue
|
Client/test2.py
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
|
| 9 |
+
os.chdir(os.path.dirname(os.path.abspath(__file__)))
|
| 10 |
+
os.makedirs("images/Stash", exist_ok=True)
|
| 11 |
+
|
| 12 |
+
db = lmdb.open("db", subdir=True, map_size=1048576)
|
| 13 |
+
|
| 14 |
+
with db.begin(write=True) as txn:
|
| 15 |
+
print(txn.get(b"test") == None)
|