a bunc of stuff
This commit is contained in:
228
modules/comix.old
Normal file
228
modules/comix.old
Normal file
@@ -0,0 +1,228 @@
|
||||
{
|
||||
"name": "Comix Reader",
|
||||
"version": "1.0.7",
|
||||
"author": "Animex",
|
||||
"description": "Comix.to Manga Reader - Fixed WAF validation, URL encoding, and Anti-Leech headers.",
|
||||
"type": "MANGA_READER",
|
||||
"requirements": ["httpx", "re", "json"]
|
||||
}
|
||||
---
|
||||
import re
|
||||
import json
|
||||
import urllib.parse
|
||||
import inspect
|
||||
import httpx
|
||||
|
||||
# Extended headers to satisfy WAF & Anti-Leech checks
|
||||
HEADERS = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Accept': 'application/json, text/plain, */*',
|
||||
'Referer': 'https://comix.to/',
|
||||
'X-Requested-With': 'XMLHttpRequest'
|
||||
}
|
||||
|
||||
async def _smart_fetch(method: str, url: str, **kwargs):
|
||||
"""Uses injected HybridClient if available, otherwise falls back to real httpx."""
|
||||
client_or_lib = globals().get('httpx')
|
||||
|
||||
func = getattr(client_or_lib, method.lower(), None)
|
||||
if func and inspect.iscoroutinefunction(func):
|
||||
resp = await func(url, **kwargs)
|
||||
return resp
|
||||
|
||||
# Fallback: real httpx.AsyncClient
|
||||
import httpx as _real_httpx
|
||||
async with _real_httpx.AsyncClient(follow_redirects=True) as client:
|
||||
resp = await getattr(client, method.lower())(url, **kwargs)
|
||||
return resp
|
||||
|
||||
def get_nested(data, *keys, default=None):
|
||||
"""Helper to safely traverse deeply nested dictionaries even if keys are None."""
|
||||
for key in keys:
|
||||
if isinstance(data, dict):
|
||||
data = data.get(key)
|
||||
else:
|
||||
return default
|
||||
return data if data is not None else default
|
||||
|
||||
async def get_title_from_mal(mal_id: int):
|
||||
"""Fetches the title from MyAnimeList via Jikan."""
|
||||
url = f"https://api.jikan.moe/v4/manga/{mal_id}"
|
||||
try:
|
||||
resp = await _smart_fetch("GET", url)
|
||||
if not resp: return None
|
||||
data = resp.json() if hasattr(resp, "json") else None
|
||||
|
||||
# Safe traversal of data['data']['title']
|
||||
return get_nested(data, 'data', 'title')
|
||||
except Exception as e:
|
||||
print(f"[Comix] MAL Fetch Error: {e}")
|
||||
return None
|
||||
|
||||
async def search_manga(query: str):
|
||||
"""Searches Comix.to and returns (manga_id, hash_id, slug)."""
|
||||
if not query: return None
|
||||
|
||||
# Safely URL encode parameters (prevents WAF bracket blocks)
|
||||
params = {"keyword": query, "order[relevance]": "desc"}
|
||||
qs = urllib.parse.urlencode(params)
|
||||
url = f"https://comix.to/api/v2/manga?{qs}"
|
||||
|
||||
try:
|
||||
resp = await _smart_fetch("GET", url, headers=HEADERS)
|
||||
print(f"[Comix] Search status: {getattr(resp, 'status_code', 500)}")
|
||||
data = resp.json() if hasattr(resp, "json") else None
|
||||
if data is None:
|
||||
return None
|
||||
|
||||
# Safely get first item from result -> items
|
||||
items = get_nested(data, 'result', 'items', default=[])
|
||||
if items and isinstance(items, list) and len(items) > 0:
|
||||
first = items[0]
|
||||
if isinstance(first, dict):
|
||||
# Return manga_id too for WAF API fallback purposes
|
||||
return first.get('manga_id'), first.get('hash_id'), first.get('slug')
|
||||
except Exception as e:
|
||||
print(f"[Comix] Search Error: {e}")
|
||||
return None
|
||||
|
||||
async def get_chapters(mal_id: int):
|
||||
try:
|
||||
print(f"[Comix] get_chapters called for MAL ID: {mal_id}")
|
||||
|
||||
title = await get_title_from_mal(mal_id)
|
||||
if not title: return None
|
||||
|
||||
manga_info = await search_manga(title)
|
||||
if not manga_info: return None
|
||||
|
||||
manga_id, hash_id, slug = manga_info
|
||||
|
||||
# Paginate since API caps at 100 per request
|
||||
all_items = []
|
||||
page = 1
|
||||
|
||||
while True:
|
||||
# Dynamically spoof the Referer for the specific manga to bypass Anti-Leech
|
||||
req_headers = HEADERS.copy()
|
||||
req_headers["Referer"] = f"https://comix.to/title/{hash_id}-{slug}"
|
||||
|
||||
# Safely encode the query string to prevent 403 Bracket Rejection
|
||||
params = {
|
||||
"order[number]": "asc",
|
||||
"limit": 100,
|
||||
"page": page
|
||||
}
|
||||
qs = urllib.parse.urlencode(params)
|
||||
|
||||
# Primary Try: Try requesting chapters using the Hash ID
|
||||
url = f"https://comix.to/api/v2/manga/{hash_id}/chapters?{qs}&_=xQm9tJfLwGhz_0Eq8S_YAHYkwp-q1PLfm50W5QJnyd1NnNYpAjXjyCoAzoOLRgUaJOoxWS0NeDGz_rNrbqBjLLP1H9qi"
|
||||
resp = await _smart_fetch("GET", url, headers=req_headers)
|
||||
|
||||
data = resp.json() if hasattr(resp, "json") else None
|
||||
|
||||
# Fallback: If framework validation fails (400, 403, 404), it might be strictly
|
||||
# expecting the internal integer primary key instead of the string hash.
|
||||
if data and data.get("status") in [400, 403, 404]:
|
||||
print(f"[Comix] Hash ID rejected ({data.get('status')}). Falling back to Integer Manga ID...")
|
||||
url_fallback = f"https://comix.to/api/v2/manga/{manga_id}/chapters?{qs}&_=xQm9tJfLwGhz_0Eq8S_YAHYkwp-q1PLfm50W5QJnyd1NnNYpAjXjyCoAzoOLRgUaJOoxWS0NeDGz_rNrbqBjLLP1H9qi"
|
||||
resp = await _smart_fetch("GET", url_fallback, headers=req_headers)
|
||||
data = resp.json() if hasattr(resp, "json") else None
|
||||
|
||||
if data is None or data.get("status") != 200:
|
||||
error_msg = data.get('message') if data else getattr(resp, 'text', '')[:200]
|
||||
print(f"[Comix] Bad response on page {page}: {error_msg}")
|
||||
break
|
||||
|
||||
items = get_nested(data, 'result', 'items', default=[])
|
||||
pagination = get_nested(data, 'result', 'pagination', default={})
|
||||
last_page = pagination.get('last_page', 1)
|
||||
|
||||
if not items:
|
||||
break
|
||||
|
||||
all_items.extend(items)
|
||||
print(f"[Comix] Page {page}/{last_page} — got {len(items)} chapters, total so far: {len(all_items)}")
|
||||
|
||||
if page >= last_page:
|
||||
break
|
||||
|
||||
page += 1
|
||||
|
||||
seen_numbers = {}
|
||||
formatted = []
|
||||
for item in all_items:
|
||||
if not isinstance(item, dict): continue
|
||||
num = str(item.get('number', '0'))
|
||||
|
||||
# Safely fallback to any available ID key
|
||||
c_id = item.get('chapter_id') or item.get('id') or item.get('hash_id')
|
||||
|
||||
if num not in seen_numbers:
|
||||
seen_numbers[num] = True
|
||||
formatted.append({
|
||||
"title": item.get('name') or f"Chapter {num}",
|
||||
"url": f"{hash_id}:{slug}:{c_id}",
|
||||
"chapter_number": num,
|
||||
"is_external": False
|
||||
})
|
||||
|
||||
def safe_float(v):
|
||||
try: return float(v)
|
||||
except: return 0.0
|
||||
|
||||
formatted.sort(key=lambda x: safe_float(x['chapter_number']), reverse=True)
|
||||
return formatted
|
||||
except Exception as e:
|
||||
print(f"[Comix] Chapter Fetch Exception: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return None
|
||||
|
||||
async def get_chapter_images(mal_id: int, chapter_num: str):
|
||||
"""Public API: Scrapes image URLs from the chapter page."""
|
||||
try:
|
||||
chapters = await get_chapters(mal_id)
|
||||
if not chapters: return None
|
||||
|
||||
target_chapter = None
|
||||
target_f = None
|
||||
try: target_f = float(chapter_num)
|
||||
except: pass
|
||||
|
||||
for ch in chapters:
|
||||
if target_f is not None:
|
||||
try:
|
||||
if float(ch["chapter_number"]) == target_f:
|
||||
target_chapter = ch
|
||||
break
|
||||
except: pass
|
||||
if ch["chapter_number"] == str(chapter_num):
|
||||
target_chapter = ch
|
||||
break
|
||||
|
||||
if not target_chapter: return None
|
||||
|
||||
hash_id, slug, chapter_id = target_chapter["url"].split(":")
|
||||
url = f"https://comix.to/title/{hash_id}-{slug}/{chapter_id}-chapter-{chapter_num}"
|
||||
|
||||
# Mirror the Referer just as we do for chapters
|
||||
req_headers = HEADERS.copy()
|
||||
req_headers["Referer"] = f"https://comix.to/title/{hash_id}-{slug}"
|
||||
|
||||
resp = await _smart_fetch("GET", url, headers=req_headers)
|
||||
if not resp or not hasattr(resp, "text"): return None
|
||||
|
||||
regex = r'["\\]*images["\\]*\s*:\s*(\[[^\]]*\])'
|
||||
match = re.search(regex, resp.text, re.DOTALL)
|
||||
|
||||
if match:
|
||||
raw_json = match.group(1).replace('\\"', '"')
|
||||
images_data = json.loads(raw_json)
|
||||
if isinstance(images_data, list):
|
||||
return [img['url'] for img in images_data if isinstance(img, dict) and 'url' in img]
|
||||
|
||||
return []
|
||||
except Exception as e:
|
||||
print(f"[Comix] Scraper Error: {e}")
|
||||
return None
|
||||
Reference in New Issue
Block a user