comments

.gitignore

@@ -1,6 +1,7 @@
 .env
 db
 images
+comments
 merge_dev.bat
 __pycache__
 *.png

Client/comments.py

@@ -0,0 +1,140 @@
+import os
+import json
+import requests
+from tqdm import tqdm
+
+
+COMMENTS_URL = "https://www.pixiv.net/ajax/illusts/comments/roots"
+COMMENTS_LIMIT = 30
+
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:126.0) Gecko/20100101 Firefox/126.0",
+    "Referer": "https://www.pixiv.net/",
+}
+
+
+def read_dotenv_value(path, key):
+    try:
+        with open(path, "r") as env_file:
+            for line in env_file:
+                line = line.strip()
+                if not line or line.startswith("#") or "=" not in line:
+                    continue
+                k, v = line.split("=", 1)
+                if k == key:
+                    return v
+    except FileNotFoundError:
+        return None
+    return None
+
+
+def get_phpsessid():
+    phpsessid = os.getenv("PHPSESSID")
+    if phpsessid:
+        return phpsessid
+    env_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".env"))
+    phpsessid = read_dotenv_value(env_path, "PHPSESSID")
+    if phpsessid:
+        return phpsessid
+    raise RuntimeError("PHPSESSID is not set in the environment or .env")
+
+
+def build_session(phpsessid):
+    session = requests.Session()
+    session.cookies.update({"PHPSESSID": phpsessid})
+    session.headers.update(HEADERS)
+    return session
+
+
+def fetch_comments(post_id, session, limit=COMMENTS_LIMIT):
+    offset = 0
+    results = []
+
+    while True:
+        params = {"illust_id": post_id, "offset": offset, "limit": limit}
+        headers = {"Referer": f"https://www.pixiv.net/artworks/{post_id}"}
+        response = session.get(COMMENTS_URL, params=params, headers=headers, timeout=30)
+        response.raise_for_status()
+        payload = response.json()
+
+        if payload.get("error"):
+            message = payload.get("message") or "Unknown error"
+            raise RuntimeError(f"Pixiv error for {post_id}: {message}")
+
+        body = payload.get("body") or {}
+        comments = body.get("comments") or []
+
+        for comment in comments:
+            text = comment.get("comment") or ""
+            if not text and comment.get("stampId"):
+                text = f"[stamp:{comment['stampId']}]"
+            results.append(
+                {
+                    "name": comment.get("userName") or "",
+                    "Comment": text,
+                }
+            )
+
+        if not body.get("hasNext"):
+            break
+        offset += limit
+
+    return results
+
+
+def parse_indexes(inputs):
+    indexes = []
+    for inp in inputs:
+        if "-" in inp:
+            start, end = map(int, inp.split("-"))
+            indexes.extend(range(start - 1, end))
+        elif inp.isdigit():
+            indexes.append(int(inp) - 1)
+    return indexes
+
+
+def main():
+    os.chdir(os.path.dirname(os.path.abspath(__file__)))
+    os.makedirs("comments", exist_ok=True)
+
+    valid = [f for f in os.listdir() if f.endswith(".txt")]
+    for idx, file in enumerate(valid):
+        print(f"{idx + 1}: {file}")
+
+    if not valid:
+        print("No .txt files found in the Client directory.")
+        return
+
+    inputs = input("Enter the index of the file: ").split()
+    indexes = parse_indexes(inputs)
+
+    phpsessid = get_phpsessid()
+    session = build_session(phpsessid)
+
+    for index in indexes:
+        if index < 0 or index >= len(valid):
+            continue
+        group_name = valid[index].rsplit(".", 1)[0]
+        with open(valid[index], "r") as f:
+            post_ids = f.read().split()
+
+        if not post_ids:
+            continue
+
+        comments_by_post = {}
+        for post_id in tqdm(post_ids, desc=f"Fetching {group_name}"):
+            try:
+                comments_by_post[str(post_id)] = fetch_comments(post_id, session)
+            except Exception as exc:
+                print(f"Failed to fetch comments for {post_id}: {exc}")
+                comments_by_post[str(post_id)] = []
+
+        output_path = os.path.join("comments", f"{group_name}.json")
+        with open(output_path, "w", encoding="utf-8") as f:
+            json.dump(comments_by_post, f, indent=2, ensure_ascii=False)
+
+        print(f"Saved comments to {output_path}")
+
+
+if __name__ == "__main__":
+    main()