Bug fixes for Login and WELIB (#242)

Fix login (when using latest CWA in dev)
Add PRIORITIZE_WELIB option
libgen seems to be back, revert the url rewrite

Should fix #242 and #226

app.py

@@ -357,7 +357,10 @@ def authenticate() -> bool:
 
     # Validate credentials against database
     try:
-        conn = sqlite3.connect(CWA_DB_PATH)
+        # Open database in true read-only mode to avoid journal/WAL writes on RO mounts
+        db_path = os.fspath(CWA_DB_PATH)
+        db_uri = f"file:{db_path}?mode=ro&immutable=1"
+        conn = sqlite3.connect(db_uri, uri=True)
         cur = conn.cursor()
         cur.execute("SELECT password FROM user WHERE name = ?", (username,))
         row = cur.fetchone()

book_manager.py

@@ -9,7 +9,7 @@ from bs4 import BeautifulSoup, Tag, NavigableString, ResultSet
 import downloader
 from logger import setup_logger
 from config import SUPPORTED_FORMATS, BOOK_LANGUAGE, AA_BASE_URL
-from env import AA_DONATOR_KEY, USE_CF_BYPASS
+from env import AA_DONATOR_KEY, USE_CF_BYPASS, PRIORITIZE_WELIB
 from models import BookInfo, SearchFilters
 
 logger = setup_logger(__name__)
@@ -198,7 +198,7 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
             ):
                 libgen_url = url["href"]
                 # TODO : Temporary fix ? Maybe get URLs from https://open-slum.org/ ?
-                libgen_url = libgen_url = re.sub(r'libgen\.(\w+)', 'libgen.bz', url["href"])
+                libgen_url = libgen_url = re.sub(r'libgen\.(\w+)', 'libgen.gs', url["href"])
                 external_urls_libgen.add(libgen_url)
             elif url.text.strip().lower().startswith("z-lib"):
                 if ".onion/" not in url["href"]:
@@ -206,11 +206,13 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
         except:
             pass
 
+    external_urls_welib = _get_download_urls_from_welib(book_id) if USE_CF_BYPASS else set()
 
     urls = []
+    urls += list(external_urls_welib) if PRIORITIZE_WELIB else []
     urls += list(slow_urls_no_waitlist) if USE_CF_BYPASS else []
     urls += list(external_urls_libgen)
-    urls += list( _get_download_urls_from_welib(book_id))  if USE_CF_BYPASS else []
+    urls += list(external_urls_welib) if not PRIORITIZE_WELIB else []
     urls += list(slow_urls_with_waitlist)  if USE_CF_BYPASS else []
     urls += list(external_urls_z_lib)
 
@@ -244,9 +246,10 @@ def _parse_book_info_page(soup: BeautifulSoup, book_id: str) -> BookInfo:
 
     return book_info
 
-def _get_download_urls_from_welib(book_id: str) -> List[str]:
+def _get_download_urls_from_welib(book_id: str) -> set[str]:
     """Get download urls from welib.org."""
     url = f"https://welib.org/md5/{book_id}"
+    logger.info(f"Getting download urls from welib.org for {book_id}. While this uses the bypasser, it will not start downloading them yet.")
     html = downloader.html_get_page(url, use_bypasser=True)
     if not html:
         return []

env.py

@@ -25,7 +25,9 @@ _BOOK_LANGUAGE = os.getenv("BOOK_LANGUAGE", "en").lower()
 _CUSTOM_SCRIPT = os.getenv("CUSTOM_SCRIPT", "").strip()
 FLASK_HOST = os.getenv("FLASK_HOST", "0.0.0.0")
 FLASK_PORT = int(os.getenv("FLASK_PORT", "8084"))
-DEBUG = string_to_bool(os.getenv("DEBUG", "False"))
+DEBUG = string_to_bool(os.getenv("DEBUG", "false"))
+PRIORITIZE_WELIB = string_to_bool(os.getenv("PRIORITIZE_WELIB", "false"))
+
 # If debug is true, we want to log everything
 if DEBUG:
     LOG_LEVEL = "DEBUG"

readme.md

@@ -82,6 +82,7 @@ Note that if using TOR, the TZ will be calculated automatically based on IP.
 | `BOOK_LANGUAGE`        | Preferred language for books                              | `en`                              |
 | `AA_DONATOR_KEY`       | Optional Donator key for Anna's Archive fast download API | ``                                |
 | `USE_BOOK_TITLE`       | Use book title as filename instead of ID                  | `false`                           |
+| `PRIORITIZE_WELIB`     | When downloading, download from WELIB first instead of AA | `false`                           |
 
 If you change `BOOK_LANGUAGE`, you can add multiple comma separated languages, such as `en,fr,ru` etc.  
 
@@ -90,7 +91,7 @@ If you change `BOOK_LANGUAGE`, you can add multiple comma separated languages, s
 | Variable               | Description                                               | Default Value                     |
 | ---------------------- | --------------------------------------------------------- | --------------------------------- |
 | `AA_BASE_URL`          | Base URL of Annas-Archive (could be changed for a proxy)  | `https://annas-archive.org`       |
-| `USE_CF_BYPASS`        | Disable CF bypass and use alternative links instead       | `true`                           |
+| `USE_CF_BYPASS`        | Disable CF bypass and use alternative links instead       | `true`                            |
 
 If you are a donator on AA, you can use your Key in `AA_DONATOR_KEY` to speed up downloads and bypass the wait times.
 If disabling the cloudflare bypass, you will be using alternative download hosts, such as libgen or z-lib, but they usually have a delay before getting the more recent books and their collection is not as big as aa's. But this setting should work for the majority of books.