web-novel-scraper 1.0.4__py3-none-any.whl → 1.1.1__py3-none-any.whl

web_novel_scraper/decode.py

@@ -12,11 +12,17 @@ logger = logger_manager.create_logger('DECODE HTML')
 
 CURRENT_DIR = Path(__file__).resolve().parent
 
-DECODE_GUIDE_FILE = os.getenv('DECODE_GUIDE_FILE', f'{
-                              CURRENT_DIR}/decode_guide/decode_guide.json')
+DECODE_GUIDE_FILE = os.getenv('DECODE_GUIDE_FILE', f'{CURRENT_DIR}/decode_guide/decode_guide.json')
 
 XOR_SEPARATOR = "XOR"
 
+DEFAULT_REQUEST_CONFIG = {
+    "force_flaresolver": False,
+    "request_retries": 3,
+    "request_timeout": 20,
+    "request_time_between_retries": 3
+}
+
 try:
     with open(DECODE_GUIDE_FILE, 'r', encoding='UTF-8') as f:
         DECODE_GUIDE = json.load(f)
@@ -37,11 +43,30 @@ except Exception as e:
 class Decoder:
     host: str
     decode_guide: json
+    request_config: dict
 
     def __init__(self, host: str):
         self.host = host
         self.decode_guide = self._get_element_by_key(
             DECODE_GUIDE, 'host', host)
+        host_request_config = self.get_request_config()
+        self.request_config = DEFAULT_REQUEST_CONFIG | host_request_config
+
+    def get_request_config(self) -> dict:
+        request_config = self.decode_guide.get('request_config')
+        if request_config:
+            logger.debug(f'Host "{self.host}" has a custom request configuration on the Decode Guide file.')
+            return request_config
+
+        return DEFAULT_REQUEST_CONFIG
+
+    def is_index_inverted(self, host:str = None) -> bool:
+        if host:
+            decode_guide = self._get_element_by_key(DECODE_GUIDE, 'host', host)
+        else:
+            decode_guide = self.decode_guide
+
+        return decode_guide.get('index', {}).get('inverted', False)
 
     def get_chapter_urls(self, html: str) -> list[str]:
         logger.debug('Obtaining chapter URLs...')
@@ -131,7 +156,7 @@ class Decoder:
             return ' '.join(elements)
         return elements
 
-    def has_pagination(self, host: str = None):
+    def has_pagination(self, host: str = None) -> bool:
         if host:
             decode_guide = self._get_element_by_key(DECODE_GUIDE, 'host', host)
             return decode_guide['has_pagination']
@@ -246,9 +271,8 @@ class Decoder:
         return elements[0]
 
     @staticmethod
-    def _get_element_by_key(json_data, key, value):
+    def _get_element_by_key(json_data, key: str, value: str):
         for item in json_data:
             if item[key] == value:
                 return item
-        logger.warning('Host not found, using default decoder.')
         return json_data[0]

web_novel_scraper/decode_guide/decode_guide.json

@@ -130,10 +130,10 @@
             }
         },
         "content": {
-            "element": "div#chr-content",
+            "element": null,
             "id": null,
             "class": null,
-            "selector": null,
+            "selector": "div#chr-content p",
             "attributes": null,
             "array": true
         },
@@ -160,6 +160,9 @@
     },
     {
         "host": "novelbin.com",
+        "request_config": {
+            "force_flaresolver": "true"
+        },
         "has_pagination": false,
         "title": {
             "element": "h2 a.chr-title",
@@ -295,5 +298,40 @@
                 "key": "href"
             }
         }
+    },
+    {
+        "host": "scribblehub.com",
+        "request_config": {
+            "force_flaresolver": "true",
+            "request_timeout": 60
+        },
+        "has_pagination": true,
+        "title": {
+            "selector": "div.chapter-title",
+            "extract": {
+                "type": "text"
+            }
+        },
+        "content": {
+            "selector": "div.chp_raw p",
+            "array": true
+        },
+        "index": {
+            "selector": "div.toc ol li a",
+            "array": true,
+            "inverted": true,
+            "extract": {
+                "type": "attr",
+                "key": "href"
+            }
+        },
+        "next_page": {
+            "selector": "div ul.simple-pagination li a.next",
+            "array": false,
+            "extract": {
+                "type": "attr",
+                "key": "href"
+            }
+        }
     }
 ]

web_novel_scraper/file_manager.py

@@ -45,10 +45,10 @@ class FileManager:
                  novel_config_dir: str = None,
                  read_only: bool = False):
         logger.debug(f'Initializing FileManager for novel: {novel_title}, read_only: {read_only}')
-        novel_base_dir = novel_base_dir if novel_base_dir else f'{
-            SCRAPER_BASE_DATA_DIR}/{novel_title}'
-        novel_config_dir = novel_config_dir if novel_config_dir else f'{
-            SCRAPER_BASE_CONFIG_DIR}/{novel_title}'
+        novel_base_dir = novel_base_dir if novel_base_dir else \
+                        f'{SCRAPER_BASE_DATA_DIR}/{novel_title}'
+        novel_config_dir = novel_config_dir if novel_config_dir else \
+                            f'{SCRAPER_BASE_CONFIG_DIR}/{novel_title}'
         
         logger.debug(f'Using base dir: {novel_base_dir}, config dir: {novel_config_dir}')
         
@@ -243,8 +243,7 @@ def _save_content_to_file(filepath: Path, content: str | dict, is_json: bool = F
     except (OSError, IOError) as e:
         logger.error(f'Error saving file "{filepath}": {e}')
     except Exception as e:
-        logger.error(f'Unexpected error saving file "{
-                     filepath}": {e}', exc_info=True)
+        logger.error(f'Unexpected error saving file "{filepath}": {e}', exc_info=True)
 
 
 def _read_content_from_file(filepath: Path, bytes: bool = False) -> str:
@@ -263,8 +262,7 @@ def _read_content_from_file(filepath: Path, bytes: bool = False) -> str:
         logger.error(f'Error reading file "{filepath}": {e}')
     except Exception as e:
         # Log for unexpected errors
-        logger.error(f'Unexpected error reading file "{
-                     filepath}": {e}', exc_info=True)
+        logger.error(f'Unexpected error reading file "{filepath}": {e}', exc_info=True)
 
 
 def _delete_file(filepath: Path) -> None:
@@ -280,8 +278,7 @@ def _delete_file(filepath: Path) -> None:
         logger.error(f'Error deleting file "{filepath}": {e}')
     except Exception as e:
         # Log any unexpected errors
-        logger.error(f'Unexpected error deleting file "{
-                     filepath}": {e}', exc_info=True)
+        logger.error(f'Unexpected error deleting file "{filepath}": {e}', exc_info=True)
 
 
 def _copy_file(source: Path, destination: Path) -> bool:

web_novel_scraper/novel_scraper.py

@@ -10,7 +10,7 @@ from .decode import Decoder
 from .file_manager import FileManager
 from . import utils
 
-from . import request_manager
+from .request_manager import get_html_content
 
 logger = logger_manager.create_logger('NOVEL SCRAPPING')
 
@@ -39,9 +39,11 @@ class Metadata:
         """
         Dynamic string representation of the configuration.
         """
-        attributes = [f"{field.name}={
-            getattr(self, field.name)}" for field in fields(self)]
-        return f"Metadata: \n{'\n'.join(attributes)}"
+        attributes = [(f"{field.name}="
+                       f"{getattr(self, field.name)}") for field in fields(self)]
+        attributes_str = '\n'.join(attributes)
+        return (f"Metadata: \n"
+                f"{attributes_str}")
 
 
 @dataclass_json
@@ -70,9 +72,11 @@ class ScraperBehavior:
         """
         Dynamic string representation of the configuration.
         """
-        attributes = [f"{field.name}={
-            getattr(self, field.name)}" for field in fields(self)]
-        return f"Scraper Behavior: \n{'\n'.join(attributes)}"
+        attributes = [(f"{field.name}="
+                       f"{getattr(self, field.name)}") for field in fields(self)]
+        attributes_str = '\n'.join(attributes)
+        return (f"Scraper Behavior: \n"
+                f"{attributes_str}")
 
 
 @dataclass_json(undefined=Undefined.EXCLUDE)
@@ -169,7 +173,9 @@ class Novel:
             f"TOC Info: {toc_info}",
             f"Host: {self.host}"
         ]
-        return f"Novel Info: \n{'\n'.join(attributes)}"
+        attributes_str = '\n'.join(attributes)
+        return (f"Novel Info: \n"
+                f"{attributes_str}")
 
     # NOVEL PARAMETERS MANAGEMENT
 
@@ -186,8 +192,7 @@ class Novel:
             self.metadata.tags.append(tag)
             self.save_novel()
             return True
-        logger.warning(f'Tag "{tag}" already exists on novel {
-                       self.metadata.novel_title}')
+        logger.warning(f'Tag "{tag}" already exists on novel {self.metadata.novel_title}')
         return False
 
     def remove_tag(self, tag: str) -> bool:
@@ -195,8 +200,7 @@ class Novel:
             self.metadata.tags.remove(tag)
             self.save_novel()
             return True
-        logger.warning(f'Tag "{tag}" doesn\'t exist on novel {
-                       self.metadata.novel_title}')
+        logger.warning(f'Tag "{tag}" doesn\'t exist on novel {self.metadata.novel_title}')
         return False
 
     def set_cover_image(self, cover_image_path: str) -> bool:
@@ -273,8 +277,16 @@ class Novel:
             if chapters_url_from_toc_content is None:
                 logger.error('Chapters url not found on toc_content')
                 return False
-            self.chapters_url_list = [*self.chapters_url_list,
-                                      *chapters_url_from_toc_content]
+                # First we save a list of lists in case we need to invert the orderAdd commentMore actions
+            self.chapters_url_list.append(chapters_url_from_toc_content)
+
+        invert = self.decoder.is_index_inverted()
+        self.chapters_url_list = [
+            chapter
+            for chapters_url in (self.chapters_url_list[::-1] if invert else self.chapters_url_list)
+            for chapter in chapters_url
+        ]
+
         if self.scraper_behavior.auto_add_host:
             self.chapters_url_list = [
                 f'https://{self.host}{chapter_url}' for chapter_url in self.chapters_url_list]
@@ -298,11 +310,9 @@ class Novel:
         chapter_list = "Chapters List:\n"
         for i, chapter in enumerate(self.chapters):
             chapter_list += f"Chapter {i + 1}:\n"
-            chapter_list += f"  Title: {
-                chapter.chapter_title if chapter.chapter_title else 'Title not yet scrapped'}\n"
+            chapter_list += f"  Title: {chapter.chapter_title if chapter.chapter_title else 'Title not yet scrapped'}\n"
             chapter_list += f"  URL: {chapter.chapter_url}\n"
-            chapter_list += f"  Filename: {
-                chapter.chapter_html_filename if chapter.chapter_html_filename else 'File not yet requested'}\n"
+            chapter_list += f"  Filename: {chapter.chapter_html_filename if chapter.chapter_html_filename else 'File not yet requested'}\n"
         return chapter_list
 
     def scrap_chapter(self, chapter_url: str = None, chapter_idx: int = None, update_html: bool = False) -> Chapter:
@@ -379,8 +389,7 @@ class Novel:
                 chapter = self._get_chapter(
                     chapter=chapter, reload=update_html)
                 if not chapter.chapter_html_filename:
-                    logger.critical(f'Error requesting chapter {
-                                    i} with url {chapter.chapter_url}')
+                    logger.critical(f'Error requesting chapter {i} with url {chapter.chapter_url}')
                     return False
 
                 self._add_or_update_chapter_data(chapter=chapter, link_idx=i,
@@ -402,16 +411,15 @@ class Novel:
             self.sync_toc()
 
         if start_chapter > len(self.chapters):
-            logger.info(f'The start chapter is bigger than the number of chapters saved ({
-                        len(self.chapters)})')
+            logger.info(f'The start chapter is bigger than the number of chapters saved ({len(self.chapters)})')
             return
 
         if not end_chapter:
             end_chapter = len(self.chapters)
         elif end_chapter > len(self.chapters):
             end_chapter = len(self.chapters)
-            logger.info(f'The end chapter is bigger than the number of chapters, automatically setting it to {
-                        end_chapter}.')
+            logger.info(f'The end chapter is bigger than the number of chapters, '
+                        f'automatically setting it to {end_chapter}.')
 
         idx = 1
         start = start_chapter
@@ -421,8 +429,8 @@ class Novel:
                                                  end_chapter=end,
                                                  collection_idx=idx)
             if not result:
-                logger.critical(f'Error with saving novel to epub, with start chapter: {
-                                start_chapter} and end chapter: {end_chapter}')
+                logger.critical(f'Error with saving novel to epub, with start chapter: '
+                                f'{start_chapter} and end chapter: {end_chapter}')
                 return False
             start = start + chapters_by_book
             idx = idx + 1
@@ -464,6 +472,16 @@ class Novel:
             toc = self.decoder.clean_html(toc, hard_clean=hard_clean)
             self.file_manager.update_toc(toc, i)
 
+    def _request_html_content(self, url: str) -> Optional[str]:
+        request_config = self.decoder.request_config
+        force_flaresolver = request_config.get('force_flaresolver') or self.scraper_behavior.force_flaresolver
+        html_content = get_html_content(url,
+                                        retries=request_config.get('request_retries'),
+                                        timeout=request_config.get('request_timeout'),
+                                        time_between_retries=request_config.get('request_time_between_retries'),
+                                        force_flaresolver=force_flaresolver)
+        return html_content
+
     def _get_chapter(self,
                      chapter: Chapter,
                      reload: bool = False) -> Chapter | None:
@@ -481,8 +499,7 @@ class Novel:
                 return chapter
 
         # Fetch fresh content
-        chapter.chapter_html = request_manager.get_html_content(chapter.chapter_url,
-                                                                force_flaresolver=self.scraper_behavior.force_flaresolver)
+        chapter.chapter_html = self._request_html_content(chapter.chapter_url)
         if not chapter.chapter_html:
             logger.error(f'No content found on link {chapter.chapter_url}')
             return chapter
@@ -501,7 +518,11 @@ class Novel:
             if content:
                 return content
 
-        content = request_manager.get_html_content(url)
+        if utils.check_incomplete_url(url):
+            url = self.toc_main_url + url
+
+        # Fetch fresh content
+        content = self._request_html_content(url)
         if not content:
             logger.warning(f'No content found on link {url}')
             sys.exit(1)
@@ -679,8 +700,7 @@ class Novel:
         idx_start = start_chapter - 1
         idx_end = end_chapter
         # We create the epub book
-        book_title = f'{self.metadata.novel_title} Chapters {
-            start_chapter} - {end_chapter}'
+        book_title = f'{self.metadata.novel_title} Chapters {start_chapter} - {end_chapter}'
         calibre_collection = None
         # If collection_idx is set, we create a calibre collection
         if collection_idx:
@@ -692,8 +712,7 @@ class Novel:
             book = self._add_chapter_to_epub_book(chapter=chapter,
                                                   book=book)
             if book is None:
-                logger.critical(f'Error saving epub {book_title}, could not decode chapter {
-                                chapter} using host {self.host}')
+                logger.critical(f'Error saving epub {book_title}, could not decode chapter {chapter} using host {self.host}')
                 return False
 
         book.add_item(epub.EpubNcx())

web_novel_scraper/request_manager.py

@@ -4,6 +4,7 @@ from . import logger_manager
 from dotenv import load_dotenv
 import json
 import time
+from typing import Optional
 
 load_dotenv()
 
@@ -13,45 +14,52 @@ FORCE_FLARESOLVER = os.getenv('FORCE_FLARESOLVER', '0') == '1'
 
 logger = logger_manager.create_logger('GET HTML CONTENT')
 
-def get_request(url: str,
-                timeout: int = 20,
-                retries: int = 3,
-                time_between_retries: int = 1) -> requests.Response | None:
-    logger.debug(f'Starting get_request for {url} with timeout={timeout}, retries={retries}, time_between_retries={time_between_retries}')
+
+def _get_request(url: str,
+                 timeout: int,
+                 retries: int,
+                 time_between_retries: int) -> Optional[requests.Response]:
+    logger.debug(
+        f'Starting get_request for "{url}" with timeout={timeout}, '
+        f'retries={retries}, '
+        f'time_between_retries={time_between_retries}')
     for attempt in range(retries):
-        logger.debug(f'Attempt {attempt + 1} for {url}')
+        logger.debug(f'Attempt {attempt + 1} for "{url}"')
         try:
             response = requests.get(url, timeout=timeout)
             response.raise_for_status()
-            logger.debug(f'Successful response for {url} on attempt {attempt + 1}')
+            logger.debug(f'Successful response for "{url}" on attempt {attempt + 1}')
             return response
         except requests.exceptions.ConnectionError as e:
-            logger.error(f'Connection error ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Connection error ({attempt + 1}/{retries}): {e}')
         except requests.exceptions.Timeout as e:
-            logger.error(f'Request timed out ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Request timed out ({attempt + 1}/{retries}): {e}')
         except requests.exceptions.HTTPError as e:
-            logger.error(f'HTTP error ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'HTTP error ({attempt + 1}/{retries}): {e}')
         except requests.exceptions.InvalidSchema as e:
-            logger.error(f'Invalid URL schema for "{url}": {e}')
+            logger.debug(f'Invalid URL schema for "{url}": {e}')
             break  # Don't retry on invalid schema
         except requests.exceptions.RequestException as e:
-            logger.error(f'Request failed ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Request failed ({attempt + 1}/{retries}): {e}')
 
         if attempt < retries - 1:
             logger.debug(f'Waiting {time_between_retries} seconds before retrying')
             time.sleep(time_between_retries)  # Wait before retrying
-    logger.debug(f'Failed to get a successful response for {url} after {retries} attempts')
+    logger.warning(f'Failed to get a successful response for "{url}" after {retries} attempts using common HTTP Request')
     return None
 
 
-def get_request_flaresolver(url: str,
-                            timeout: int = 20,
-                            flaresolver_url: str = FLARESOLVER_URL,
-                            retries: int = 3,
-                            time_between_retries: int = 1) -> requests.Response | None:
-    logger.debug(f'Starting get_request_flaresolver for {url} with timeout={timeout}, retries={retries}, time_between_retries={time_between_retries}')
+def _get_request_flaresolver(url: str,
+                             timeout: int,
+                             retries: int,
+                             time_between_retries: int,
+                             flaresolver_url: str) -> Optional[requests.Response]:
+    logger.debug(
+        f'Starting get_request_flaresolver for "{url}" with timeout={timeout}, '
+        f'retries={retries}, '
+        f'time_between_retries={time_between_retries}')
     for attempt in range(retries):
-        logger.debug(f'Attempt {attempt + 1} for {url} using FlareSolver')
+        logger.debug(f'Attempt {attempt + 1} for "{url}" using FlareSolver')
         try:
             response = requests.post(
                 flaresolver_url,
@@ -64,71 +72,76 @@ def get_request_flaresolver(url: str,
                 timeout=timeout
             )
             response.raise_for_status()
-            logger.debug(f'Successful response for {url} on attempt {attempt + 1} using FlareSolver')
+            logger.debug(f'Successful response for "{url}" on attempt {attempt + 1} using FlareSolver')
             return response
 
         except requests.exceptions.ConnectionError as e:
-            logger.error(f'Connection error ({attempt + 1}/{retries}), check FlareSolver host: {flaresolver_url}: {e}')
+            logger.warning(f'Connection error with flaresolver (URL: "{flaresolver_url}"): {e}')
+            logger.warning(f'If the url is incorrect, set the env variable "FLARESOLVER_URL" to the correct value')
+            logger.warning('If FlareSolver is not installed in your machine, consider installing it.')
+            break # Don't retry on Connection Error
         except requests.exceptions.Timeout as e:
-            logger.error(f'Request timed out ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Request timed out ({attempt + 1}/{retries}): {e}')
         except requests.exceptions.InvalidSchema as e:
-            logger.error(f'Invalid FlareSolver URL schema "{flaresolver_url}": {e}')
+            logger.debug(f'Invalid FlareSolver URL schema "{flaresolver_url}": {e}')
             break  # Don't retry on invalid schema
         except requests.exceptions.HTTPError as e:
-            logger.error(f'HTTP error ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'HTTP error ({attempt + 1}/{retries}): {e}')
         except requests.exceptions.RequestException as e:
-            logger.error(f'Request failed ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Request failed ({attempt + 1}/{retries}): {e}')
         except json.JSONDecodeError as e:
-            logger.error(f'Invalid JSON response ({attempt + 1}/{retries}): {e}')
+            logger.debug(f'Invalid JSON response ({attempt + 1}/{retries}): {e}')
 
         if attempt < retries - 1:
             logger.debug(f'Waiting {time_between_retries} seconds before retrying')
             time.sleep(time_between_retries)  # Wait before retrying
-    logger.debug(f'Failed to get a successful response for {url} using FlareSolver after {retries} attempts')
+
+    logger.warning(f'Failed to get a successful response for "{url}" using FlareSolver after {retries} attempts')
     return None
 
 
 def get_html_content(url: str,
-                     retries: int = 5,
-                     flaresolver: bool = True,
+                     retries: int = 3,
+                     timeout: int = 20,
+                     time_between_retries: int = 3,
                      flaresolver_url: str = FLARESOLVER_URL,
-                     time_between_retries: int = 1,
-                     force_flaresolver: bool = FORCE_FLARESOLVER) -> str | None:
-    logger.debug(f'Starting get_html_content for {url} with retries={retries}, flaresolver={flaresolver}, flaresolver_url={flaresolver_url}, time_between_retries={time_between_retries}, force_flaresolver={force_flaresolver}')
+                     force_flaresolver: bool = FORCE_FLARESOLVER) -> Optional[str]:
+    logger.debug(
+        f'Requesting HTML Content for "{url}" with '
+        f'retries: "{retries}", '
+        f'timeout: "{timeout}", '
+        f'time between retries: "{time_between_retries}"')
+    if force_flaresolver:
+        logger.debug('Will directly try with FlareSolver')
+
     # First try with common HTTP request
     if not force_flaresolver:
-        response = get_request(
-            url, timeout=20, retries=retries, time_between_retries=time_between_retries)
-        if not response:
-            logger.warning(f'Failed to get response from {url} using common HTTP request')
-        elif not response.ok:
-            logger.warning(f'Response with errors from {url} using common HTTP request')
-        else:
-            logger.debug(f'Successfully retrieved HTML content from {url} using common HTTP request')
+        response = _get_request(url,
+                                timeout=timeout,
+                                retries=retries,
+                                time_between_retries=time_between_retries)
+        if response and response.ok:
+            logger.debug(f'Successfully retrieved HTML content from "{url}" using common HTTP request')
             return response.text
 
-    # If flaresolver is disabled, return None
-    if not flaresolver:
-        logger.debug(f'Flaresolver is disabled, returning None for {url}')
-        return None
-
     # Try with Flaresolver
-    logger.debug(f'Trying with Flaresolver for {url}')
-    response = get_request_flaresolver(
-        url, timeout=20, flaresolver_url=flaresolver_url, time_between_retries=time_between_retries)
-    if not response:
-        logger.critical(f'Failed to get response from {url} using FlareSolver')
-        return None
-    if not response.ok:
-        logger.critical(f'Response with errors from {url} using FlareSolver')
+    logger.debug(f'Trying with Flaresolver for "{url}"')
+    response = _get_request_flaresolver(url,
+                                timeout=timeout,
+                                retries=retries,
+                                time_between_retries=time_between_retries,
+                                flaresolver_url=flaresolver_url)
+    if not response or not response.ok:
+        logger.warning(f'Failed all attempts to get HTML content from "{url}')
         return None
 
     response_json = response.json()
     if 'solution' not in response_json:
-        logger.critical(f'No solution found in FlareSolver response for {url}')
+        logger.warning(f'No solution found in FlareSolver response for "{url}"')
         return None
     if 'response' not in response_json['solution']:
-        logger.critical(f'No response found in FlareSolver solution for {url}')
+        logger.warning(f'No response found in FlareSolver solution for "{url}"')
         return None
-    logger.debug(f'Successfully retrieved HTML content from {url} using FlareSolver')
+
+    logger.debug(f'Successfully retrieved HTML content from "{url}" using FlareSolver')
     return response_json['solution']['response']

web_novel_scraper/utils.py

@@ -64,3 +64,10 @@ def check_exclusive_params(param1: any, param2: any) -> bool:
 
 def create_volume_id(n: int):
     return f'v{n:02}'
+
+def check_incomplete_url(url: str) -> bool:
+    if url.startswith('?') or url.startswith('#'):
+        return True
+
+    parsed = urlparse(url)
+    return not parsed.scheme or not parsed.netloc

web_novel_scraper/version.py

@@ -1 +1 @@
-__version__ = "1.0.4"
+__version__ = "1.1.1"

{web_novel_scraper-1.0.4.dist-info → web_novel_scraper-1.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: web-novel-scraper
-Version: 1.0.4
+Version: 1.1.1
 Summary: Python tool that allows you to scrape web novels from various sources and save them to more readable formats like EPUB.
 Project-URL: Homepage, https://github.com/ImagineBrkr/web-novel-scraper
 Project-URL: Documentation, https://web-novel-scraper.readthedocs.io

web_novel_scraper-1.1.1.dist-info/RECORD

@@ -0,0 +1,18 @@
+web_novel_scraper/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+web_novel_scraper/__main__.py,sha256=OQQVX5CttmAkUwdrnjBSjKPaoh_boUI2ysHi3rLGOSs,17769
+web_novel_scraper/decode.py,sha256=U-78PhJ4SU2hiUmfAWeWGEBJ3YSoCW3Lupw9cUqQuI0,11013
+web_novel_scraper/file_manager.py,sha256=qAqgqtaRb7QyVtyEOW2cMhPYWdKM6nJ69weUCYKwVtM,11862
+web_novel_scraper/logger_manager.py,sha256=A-a4bhYI4YCEuSJd9E3WH_kanJ7YCASMwheBzObZK4Q,1972
+web_novel_scraper/novel_scraper.py,sha256=DsYnY15s8cZZ2w8pRvmD3_NJw54xarhcnEQdvnTD8XI,29421
+web_novel_scraper/request_manager.py,sha256=WU8LG6D_fqmDapX6wpVwpQQSItcNU8Qb9dMAlLCYI8U,6621
+web_novel_scraper/utils.py,sha256=dPp7D2ji9mC2nFydqxsJ_9vkAntA_3VTt8ZmG-F1f78,2270
+web_novel_scraper/version.py,sha256=q8_5C0f-8mHWNb6mMw02zlYPnEGXBqvOmP3z0CEwZKM,22
+web_novel_scraper/custom_processor/__init__.py,sha256=iy4tjivMjshSzc52--aa-jK53qu9VwdK-6p4vuQc6oc,103
+web_novel_scraper/custom_processor/custom_processor.py,sha256=h1MPl6JU_C2Mc7SqK70LsNQHpDzSL6QyraMIQ87HcMM,870
+web_novel_scraper/custom_processor/sites/genesis.py,sha256=xV0eybI0ieHR5gn4yWXI74l99Eayhqs16PIYs-BrPjE,1843
+web_novel_scraper/custom_processor/sites/royalroad.py,sha256=_2PsFC_w3RJCUkAPoRn-7R2jlzl3XsG4WYtRaQkp6lg,787
+web_novel_scraper/decode_guide/decode_guide.json,sha256=gNVencLtK0HmZPlubTm1wA7eatWADCxJ_LCOYWHWuA0,8556
+web_novel_scraper-1.1.1.dist-info/METADATA,sha256=ow5piBhzzo4mZ0secvHrqc4KCCt4VInpDa09Qo9l4AE,8423
+web_novel_scraper-1.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+web_novel_scraper-1.1.1.dist-info/entry_points.txt,sha256=bqRvStfvSprSJc2EJXgKIbggWOXSePHFfVIZWy_plDQ,69
+web_novel_scraper-1.1.1.dist-info/RECORD,,

web_novel_scraper-1.0.4.dist-info/RECORD

@@ -1,18 +0,0 @@
-web_novel_scraper/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-web_novel_scraper/__main__.py,sha256=OQQVX5CttmAkUwdrnjBSjKPaoh_boUI2ysHi3rLGOSs,17769
-web_novel_scraper/decode.py,sha256=0RMHx1buR01KhuXiVQwdSpCGN960Xh-iPw1eYHxLeDg,10181
-web_novel_scraper/file_manager.py,sha256=Q3DH-c8fWz9sziMps7A3p_sQoDMEpqBket07Agh-__Q,11898
-web_novel_scraper/logger_manager.py,sha256=A-a4bhYI4YCEuSJd9E3WH_kanJ7YCASMwheBzObZK4Q,1972
-web_novel_scraper/novel_scraper.py,sha256=Notk0O94HZrO-MVKDGCBL0VopApFchn13FO2_N3ZfRM,28418
-web_novel_scraper/request_manager.py,sha256=VtGpRi5b_Dp3h8viCdt7yMCb9M21Lk7oLC_Q_0EkXH8,6448
-web_novel_scraper/utils.py,sha256=vq5ROuPv04k3MhbksTe0ni_yP0i_a7T_33mkBB1DUbQ,2076
-web_novel_scraper/version.py,sha256=acuR_XSJzp4OrQ5T8-Ac5gYe48mUwObuwjRmisFmZ7k,22
-web_novel_scraper/custom_processor/__init__.py,sha256=iy4tjivMjshSzc52--aa-jK53qu9VwdK-6p4vuQc6oc,103
-web_novel_scraper/custom_processor/custom_processor.py,sha256=h1MPl6JU_C2Mc7SqK70LsNQHpDzSL6QyraMIQ87HcMM,870
-web_novel_scraper/custom_processor/sites/genesis.py,sha256=xV0eybI0ieHR5gn4yWXI74l99Eayhqs16PIYs-BrPjE,1843
-web_novel_scraper/custom_processor/sites/royalroad.py,sha256=_2PsFC_w3RJCUkAPoRn-7R2jlzl3XsG4WYtRaQkp6lg,787
-web_novel_scraper/decode_guide/decode_guide.json,sha256=IBBzbSSVO-yQ5PCY7o8ralnaonMwBpEZW1v1TStiVqc,7582
-web_novel_scraper-1.0.4.dist-info/METADATA,sha256=IhvDqK_Gz1POjzbH2cQVUYql1dhZJvdHnM9R--le0uc,8423
-web_novel_scraper-1.0.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-web_novel_scraper-1.0.4.dist-info/entry_points.txt,sha256=bqRvStfvSprSJc2EJXgKIbggWOXSePHFfVIZWy_plDQ,69
-web_novel_scraper-1.0.4.dist-info/RECORD,,