web-novel-scraper 1.0.4__py3-none-any.whl → 1.1.0__py3-none-any.whl

web_novel_scraper/decode.py

@@ -12,8 +12,7 @@ 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"
 

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
         },

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

@@ -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:
@@ -298,11 +302,9 @@ 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 +381,7 @@ 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 +403,15 @@ 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 +421,8 @@ 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
@@ -679,8 +679,7 @@ 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 +691,7 @@ 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/version.py

@@ -1 +1 @@
-__version__ = "1.0.4"
+__version__ = "1.1.0"

{web_novel_scraper-1.0.4.dist-info → web_novel_scraper-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: web-novel-scraper
-Version: 1.0.4
+Version: 1.1.0
 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-1.0.4.dist-info → web_novel_scraper-1.1.0.dist-info}/RECORD

@@ -1,18 +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=0RMHx1buR01KhuXiVQwdSpCGN960Xh-iPw1eYHxLeDg,10181
-web_novel_scraper/file_manager.py,sha256=Q3DH-c8fWz9sziMps7A3p_sQoDMEpqBket07Agh-__Q,11898
+web_novel_scraper/decode.py,sha256=QxPjoYI1t4bf0zAf_7uLRrpsboi8DwsD1BNZUiHO4gc,10150
+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=Notk0O94HZrO-MVKDGCBL0VopApFchn13FO2_N3ZfRM,28418
+web_novel_scraper/novel_scraper.py,sha256=hXIIPelRfx-jfD9VSPheg6z04I4JKxQj7wVBPlpP1go,28452
 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/version.py,sha256=LGVQyDsWifdACo7qztwb8RWWHds1E7uQ-ZqD8SAjyw4,22
 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,,
+web_novel_scraper/decode_guide/decode_guide.json,sha256=DbcfnyRNOVXZd6ar1HDCHxkKgnmR3ziJ-B4GOFcDMEs,7584
+web_novel_scraper-1.1.0.dist-info/METADATA,sha256=Llcez3yLJTICPNMAoO1aZShywK2soma1kmjl2OA3tYA,8423
+web_novel_scraper-1.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+web_novel_scraper-1.1.0.dist-info/entry_points.txt,sha256=bqRvStfvSprSJc2EJXgKIbggWOXSePHFfVIZWy_plDQ,69
+web_novel_scraper-1.1.0.dist-info/RECORD,,