web-novel-scraper 2.1.0__py3-none-any.whl → 2.1.1__py3-none-any.whl

web_novel_scraper/__main__.py

@@ -405,7 +405,6 @@ def scrap_chapter(ctx, title, chapter_url, chapter_num, update_html):
 
     chapter = novel.scrap_chapter(chapter=chapter,
                                   reload_file=update_html)
-
     click.echo(chapter)
     click.echo('Content:')
     click.echo(chapter.chapter_content)

web_novel_scraper/custom_processor/__init__.py

@@ -1,2 +1,2 @@
 from .custom_processor import CustomProcessor, ProcessorRegistry
-from .sites import royalroad, genesis
+from .sites import royalroad, genesis, fanmtl

web_novel_scraper/custom_processor/sites/fanmtl.py

@@ -0,0 +1,15 @@
+import re
+from typing import List, Optional
+from ..custom_processor import CustomProcessor, ProcessorRegistry
+
+class GenesisNextPageProcessor(CustomProcessor):
+    def process(self, html: str) -> Optional[str]:
+        pattern = r'href="([^"]+page=\d+[^"]*)">></a'
+        match = re.search(pattern, html)
+        if match is None:
+            return None
+        next_page = match.group(1)
+        next_page = next_page.replace('&amp;', '&')
+        return f'https://www.fanmtl.com{next_page}'
+
+ProcessorRegistry.register('fanmtl.com', 'next_page', GenesisNextPageProcessor())

web_novel_scraper/decode_guide/decode_guide.json

@@ -409,5 +409,32 @@
                 "key": "href"
             }
         }
+    },
+    {
+        "host": "fanmtl.com",
+        "has_pagination": true,
+        "add_host_to_chapter": true,
+        "save_title_to_content": true,
+        "title": {
+            "element": "h2",
+            "extract": {
+                "type": "text"
+            }
+        },
+        "content": {
+            "selector": "div.chapter-content p",
+            "array": true
+        },
+        "index": {
+            "selector": "ul.chapter-list li a",
+            "array": true,
+            "extract": {
+                "type": "attr",
+                "key": "href"
+            }
+        },
+        "next_page": {
+            "use_custom_processor": true
+        }
     }
 ]

web_novel_scraper/novel_scraper.py

@@ -154,7 +154,6 @@ class Novel:
             raise ValidationError("When providing toc_html, host must be explicitly provided")
 
         novel = cls(title=title, host=host, toc_main_url=toc_main_url)
-        breakpoint()
         # If toc_main_url is provided and the host isn't, extract host from URL
         if toc_main_url and not host:
             host = utils.obtain_host(toc_main_url)
@@ -1142,7 +1141,6 @@ class Novel:
 
         cover_image_content = self.file_manager.load_novel_cover()
         if cover_image_content:
-            breakpoint()
             book.set_cover('cover.jpg', cover_image_content)
             book.spine += ['cover']
 

web_novel_scraper/version.py

@@ -1 +1 @@
-__version__ = "2.1.0"
+__version__ = "2.1.1"

{web_novel_scraper-2.1.0.dist-info → web_novel_scraper-2.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: web-novel-scraper
-Version: 2.1.0
+Version: 2.1.1
 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-2.1.0.dist-info → web_novel_scraper-2.1.1.dist-info}/RECORD

@@ -1,20 +1,21 @@
 web_novel_scraper/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-web_novel_scraper/__main__.py,sha256=QI8oncZiSuyXu2D377uFq5BpAy4U6uyedEs-PfkY2Ek,18312
+web_novel_scraper/__main__.py,sha256=v6Y5FpO9EghFTLcDgsPfyMKQgz6dWgbKl2PDbC3rt-E,18311
 web_novel_scraper/config_manager.py,sha256=KVnCIVs1nsEI3W6YolTV9FejjwJXtUYhDn2dmHr9SC4,3193
 web_novel_scraper/decode.py,sha256=iLjXlKUh8UgTkgsQupVAhW-eUDxYrcOTx_EEgjV5s_A,15186
 web_novel_scraper/file_manager.py,sha256=6OZAuaUykUmS0fLzcSVyQSqcPanjEVpjrQ-0pa2vKls,16767
 web_novel_scraper/logger_manager.py,sha256=A-a4bhYI4YCEuSJd9E3WH_kanJ7YCASMwheBzObZK4Q,1972
 web_novel_scraper/models.py,sha256=7lS1Mb5h0qunNOslwCl6vQiuZGsMNw7h1BYK03yHeFM,2227
-web_novel_scraper/novel_scraper.py,sha256=hWZvi1c3Nnq4qSfLsfZPsjQj-UTlWaKwTlqyPtFe36I,50506
+web_novel_scraper/novel_scraper.py,sha256=BGTB8j7NhTzOnT93DE662KPqE_Kt2mO0tYVFz_xAbnk,50460
 web_novel_scraper/request_manager.py,sha256=yfXaPCeTu7FGiWnR3rImkaCWETfT3d5zxwOIylEP-_M,7954
 web_novel_scraper/utils.py,sha256=DO1bTgyGNqjHrBlMYdS0ljwegTSC_kYsIbxi-0KeuY8,6953
-web_novel_scraper/version.py,sha256=Xybt2skBZamGMNlLuOX1IG-h4uIxqUDGAO8MIGWrJac,22
-web_novel_scraper/custom_processor/__init__.py,sha256=iy4tjivMjshSzc52--aa-jK53qu9VwdK-6p4vuQc6oc,103
+web_novel_scraper/version.py,sha256=zPJIgPGcoSNiD0qme18OnYJYE3A9VVytlhO-V5DaAW0,22
+web_novel_scraper/custom_processor/__init__.py,sha256=isc6q3pz9MzazF8e3uRMhZD_bv8vf11ME_Jv_p7dznA,111
 web_novel_scraper/custom_processor/custom_processor.py,sha256=h1MPl6JU_C2Mc7SqK70LsNQHpDzSL6QyraMIQ87HcMM,870
+web_novel_scraper/custom_processor/sites/fanmtl.py,sha256=5eH9PeiJljYjqML7aEDU6qeUEEOPjGeIqkXyv-DY1pg,578
 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=ecIBugJ8ddzFH0rJHkonkrE6ogSXf98jVypQ-GnVDnE,10418
-web_novel_scraper-2.1.0.dist-info/METADATA,sha256=2EeY0XmULbnE6AFUgsuFPT0NYZSnwk6nVzb45rh_tow,8423
-web_novel_scraper-2.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-web_novel_scraper-2.1.0.dist-info/entry_points.txt,sha256=bqRvStfvSprSJc2EJXgKIbggWOXSePHFfVIZWy_plDQ,69
-web_novel_scraper-2.1.0.dist-info/RECORD,,
+web_novel_scraper/decode_guide/decode_guide.json,sha256=jSw2_c-UMRpGk1d9FqCaIrritJCl9y9O9m5qsokSk3E,11085
+web_novel_scraper-2.1.1.dist-info/METADATA,sha256=u-7Dy3YOk7WItvGnHVPkKIijhISoz9eoCiq51iCGE2I,8423
+web_novel_scraper-2.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+web_novel_scraper-2.1.1.dist-info/entry_points.txt,sha256=bqRvStfvSprSJc2EJXgKIbggWOXSePHFfVIZWy_plDQ,69
+web_novel_scraper-2.1.1.dist-info/RECORD,,