|
| 1 | +import hashlib |
| 2 | +import re |
| 3 | +import sys |
| 4 | +import json |
| 5 | +import time |
| 6 | +import requests |
| 7 | +import stashapi.log as log |
| 8 | +from stashapi.stashapp import StashInterface |
| 9 | + |
| 10 | + |
| 11 | + |
| 12 | +def get_all_images( |
| 13 | + client: StashInterface, |
| 14 | + skip_tags: list[str], |
| 15 | + exclude_organized: bool |
| 16 | +) -> list[dict]: |
| 17 | + """ |
| 18 | + Get all images with proper tag exclusion and organization filter |
| 19 | + """ |
| 20 | + image_filter = {} |
| 21 | + pagination = { |
| 22 | + "page": 1, |
| 23 | + "per_page": -1, # -1 gets all results at once |
| 24 | + "sort": "created_at", |
| 25 | + "direction": "ASC", |
| 26 | + } |
| 27 | + |
| 28 | + # Convert tag names to IDs |
| 29 | + tag_ids = [] |
| 30 | + for tag_name in skip_tags: |
| 31 | + tag = get_or_create_tag(client, tag_name) |
| 32 | + if tag: |
| 33 | + tag_ids.append(tag["id"]) |
| 34 | + |
| 35 | + if tag_ids: |
| 36 | + image_filter["tags"] = { |
| 37 | + "value": [], |
| 38 | + "excludes": tag_ids, |
| 39 | + "modifier": "INCLUDES_ALL", |
| 40 | + "depth": -1, |
| 41 | + } |
| 42 | + |
| 43 | + if exclude_organized: |
| 44 | + image_filter["organized"] = False # Correct field name |
| 45 | + |
| 46 | + # Maintain original parameter structure |
| 47 | + return client.find_images(f=image_filter, filter=pagination) |
| 48 | + |
| 49 | + |
| 50 | +def process_e621_post(stash: StashInterface, image_id: str, image_md5: str) -> None: |
| 51 | + """Process e621 metadata and update Stash records""" |
| 52 | + # Skip already processed images |
| 53 | + image = stash.find_image(image_id) |
| 54 | + if any(tag["name"] == "e621_tagged" for tag in image.get("tags", [])): |
| 55 | + return |
| 56 | + |
| 57 | + try: |
| 58 | + time.sleep(2) # Rate limiting |
| 59 | + response = requests.get( |
| 60 | + f"https://e621.net/posts.json?md5={image_md5}", |
| 61 | + headers={"User-Agent": "Stash-e621-Tagger/1.0"}, |
| 62 | + timeout=10 |
| 63 | + ) |
| 64 | + response.raise_for_status() |
| 65 | + post_data = response.json().get("post", {}) |
| 66 | + except Exception as e: |
| 67 | + log.error(f"e621 API error: {str(e)}") |
| 68 | + return |
| 69 | + |
| 70 | + if not post_data: |
| 71 | + return |
| 72 | + |
| 73 | + # Create essential entities |
| 74 | + e621_tag = get_or_create_tag(stash, "e621_tagged") |
| 75 | + post_url = f"https://e621.net/posts/{post_data['id']}" |
| 76 | + |
| 77 | + # Process tags |
| 78 | + tag_ids = [e621_tag["id"]] |
| 79 | + for category in ["general", "species", "character", "artist", "copyright"]: |
| 80 | + for tag in post_data.get("tags", {}).get(category, []): |
| 81 | + # Clean and validate tag |
| 82 | + clean_tag = tag.strip() |
| 83 | + if not clean_tag: |
| 84 | + continue |
| 85 | + |
| 86 | + stash_tag = get_or_create_tag(stash, clean_tag) |
| 87 | + if stash_tag: |
| 88 | + tag_ids.append(stash_tag["id"]) |
| 89 | + |
| 90 | + # Process studio |
| 91 | + studio_id = None |
| 92 | + if artists := post_data.get("tags", {}).get("artist"): |
| 93 | + studio = get_or_create_studio(stash, artists[0]) |
| 94 | + studio_id = studio["id"] |
| 95 | + |
| 96 | + # Process performers |
| 97 | + performer_ids = [] |
| 98 | + for char_tag in post_data.get("tags", {}).get("character", []): |
| 99 | + performer_name = char_tag.split('_(')[0] |
| 100 | + performer = get_or_create_performer(stash, performer_name) |
| 101 | + performer_ids.append(performer["id"]) |
| 102 | + |
| 103 | + # Update image |
| 104 | + try: |
| 105 | + stash.update_image({ |
| 106 | + "id": image_id, |
| 107 | + "urls": [post_url], |
| 108 | + "tag_ids": list(set(tag_ids)), |
| 109 | + "studio_id": studio_id, |
| 110 | + "performer_ids": performer_ids |
| 111 | + }) |
| 112 | + |
| 113 | + log.info("Image updated: ${image_id}") |
| 114 | + except Exception as e: |
| 115 | + log.error(f"Update failed: {str(e)}") |
| 116 | + |
| 117 | + |
| 118 | +def get_or_create_tag(stash: StashInterface, tag_name: str) -> dict: |
| 119 | + """Find or create tag with hierarchy handling""" |
| 120 | + # Validate tag name |
| 121 | + tag_name = tag_name.strip() |
| 122 | + if not tag_name: |
| 123 | + log.error("Attempted to create tag with empty name") |
| 124 | + return None |
| 125 | + |
| 126 | + existing = stash.find_tags(f={"name": {"value": tag_name, "modifier": "EQUALS"}}) |
| 127 | + if existing: |
| 128 | + return existing[0] |
| 129 | + |
| 130 | + parts = tag_name.split(":") |
| 131 | + parent_id = None |
| 132 | + for i in range(len(parts)): |
| 133 | + current_name = ":".join(parts[:i+1]).strip() |
| 134 | + if not current_name: |
| 135 | + continue |
| 136 | + |
| 137 | + existing = stash.find_tags(f={"name": {"value": current_name, "modifier": "EQUALS"}}) |
| 138 | + if not existing: |
| 139 | + create_data = {"name": current_name} |
| 140 | + if parent_id: |
| 141 | + create_data["parent_ids"] = [parent_id] |
| 142 | + try: |
| 143 | + new_tag = stash.create_tag(create_data) |
| 144 | + if not new_tag: |
| 145 | + log.error(f"Failed to create tag: {current_name}") |
| 146 | + return None |
| 147 | + parent_id = new_tag["id"] |
| 148 | + except Exception as e: |
| 149 | + log.error(f"Error creating tag {current_name}: {str(e)}") |
| 150 | + return None |
| 151 | + else: |
| 152 | + parent_id = existing[0]["id"] |
| 153 | + return {"id": parent_id} |
| 154 | + |
| 155 | +def get_or_create_studio(stash: StashInterface, name: str) -> dict: |
| 156 | + """Find or create studio""" |
| 157 | + studios = stash.find_studios(f={"name": {"value": name, "modifier": "EQUALS"}}) |
| 158 | + return studios[0] if studios else stash.create_studio({"name": name}) |
| 159 | + |
| 160 | + |
| 161 | +def get_or_create_performer(stash: StashInterface, name: str) -> dict: |
| 162 | + """Find or create performer""" |
| 163 | + performers = stash.find_performers(f={"name": {"value": name, "modifier": "EQUALS"}}) |
| 164 | + return performers[0] if performers else stash.create_performer({"name": name}) |
| 165 | + |
| 166 | + |
| 167 | +def scrape_image(client: StashInterface, image_id: str) -> None: |
| 168 | + """Main scraping handler""" |
| 169 | + image = client.find_image(image_id) |
| 170 | + if not image or not image.get("visual_files"): |
| 171 | + return |
| 172 | + |
| 173 | + file_data = image["visual_files"][0] |
| 174 | + filename = file_data["basename"] |
| 175 | + filename_md5 = filename.split('.')[0] |
| 176 | + final_md5 = None |
| 177 | + |
| 178 | + # First try filename-based MD5 |
| 179 | + if re.match(r"^[a-f0-9]{32}$", filename_md5): |
| 180 | + final_md5 = filename_md5 |
| 181 | + log.info(f"Using filename MD5: {final_md5}") |
| 182 | + else: |
| 183 | + # Fallback to content-based MD5 |
| 184 | + try: |
| 185 | + file_path = file_data["path"] |
| 186 | + log.info(f"Generating MD5 from file content: {file_path}") |
| 187 | + |
| 188 | + md5_hash = hashlib.md5() |
| 189 | + with open(file_path, "rb") as f: |
| 190 | + # Read file in 64kb chunks for memory efficiency |
| 191 | + for chunk in iter(lambda: f.read(65536), b""): |
| 192 | + md5_hash.update(chunk) |
| 193 | + |
| 194 | + final_md5 = md5_hash.hexdigest() |
| 195 | + log.info(f"Generated content MD5: {final_md5}") |
| 196 | + except Exception as e: |
| 197 | + log.error(f"Failed to generate MD5: {str(e)}") |
| 198 | + return |
| 199 | + |
| 200 | + if final_md5: |
| 201 | + process_e621_post(client, image_id, final_md5) |
| 202 | + else: |
| 203 | + log.warning("No valid MD5 available for processing") |
| 204 | + |
| 205 | +# Plugin setup and execution |
| 206 | +# In the main execution block: |
| 207 | +if __name__ == "__main__": |
| 208 | + json_input = json.loads(sys.stdin.read()) |
| 209 | + stash = StashInterface(json_input["server_connection"]) |
| 210 | + |
| 211 | + config = stash.get_configuration().get("plugins", {}) |
| 212 | + settings = { |
| 213 | + "SkipTags": "e621_tagged", # Add automatic filtering |
| 214 | + "ExcludeOrganized": False |
| 215 | + } |
| 216 | + settings.update(config.get("e621_tagger", {})) |
| 217 | + |
| 218 | + log.info(settings) |
| 219 | + |
| 220 | + # Get e621_tagged ID for filtering |
| 221 | + e621_tag = get_or_create_tag(stash, "e621_tagged") |
| 222 | + |
| 223 | + # Existing tags + automatic e621_tagged exclusion |
| 224 | + skip_tags = [t.strip() for t in settings["SkipTags"].split(",") if t.strip()] |
| 225 | + skip_tags.append(e621_tag["id"]) # Filter by ID instead of name |
| 226 | + |
| 227 | + images = get_all_images(stash, skip_tags, settings["ExcludeOrganized"]) |
| 228 | + |
| 229 | + # Rest of the loop remains the same |
| 230 | + for i, image in enumerate(images, 1): |
| 231 | + image_tag_names = [tag["name"] for tag in image.get("tags", [])] |
| 232 | + if any(tag in image_tag_names for tag in skip_tags): |
| 233 | + log.info(f"Skipping image {image['id']} - contains skip tag") |
| 234 | + continue |
| 235 | + |
| 236 | + log.progress(i/len(images)) |
| 237 | + scrape_image(stash, image["id"]) |
0 commit comments