Refactor: facade pattern for scrape helper

app/api/helpers/scraper.py

@@ -0,0 +1,13 @@
+from selectolax.parser import Node
+
+
+class ScrapeHelper:
+    @staticmethod
+    def get_text(node: Node, selector: str) -> str | None:
+        element = node.css_first(selector)
+        return element.text().strip() if element else None
+
+    @staticmethod
+    def get_attribute(node: Node, selector: str, attribute: str) -> str | None:
+        element = node.css_first(selector)
+        return element.attributes[attribute] if element else None

app/api/scrapers/most_viewed.py

@@ -2,7 +2,7 @@
 from selectolax.parser import Node
 
 from app.api.decorators.return_decorator import return_on_error
-from ..utils import get_text, get_attribute
+from app.api.helpers.scraper import ScrapeHelper
 from ..helpers.html_helper import HTMLHelper
 
 
@@ -16,32 +16,37 @@ def __init__(self, chart: str) -> None:
         self.chart = chart
         # Facades
         self.html_helper = HTMLHelper()
+        self.scraper_helper = ScrapeHelper()
         # Parser
         self.parser = self.html_helper.get_parser(url)
 
     @return_on_error("")
     def __get_slug(self, node: Node) -> str:
-        slug = get_attribute(node, ".manga-detail .manga-name a", "href")
+        slug = self.scraper_helper.get_attribute(
+            node, ".manga-detail .manga-name a", "href"
+        )
         return slug.replace("/", "") if slug else ""
 
     @return_on_error("")
     def __get_cover(self, node: Node) -> str:
-        cover = get_attribute(node, "img.manga-poster-img", "src")
+        cover = self.scraper_helper.get_attribute(node, "img.manga-poster-img", "src")
         return cover.replace("200x300", "500x800") if cover else ""
 
     @return_on_error("")
     def __get_views(self, node: Node) -> str:
-        views_string = get_text(node, ".fd-infor .fdi-view")
+        views_string = self.scraper_helper.get_text(node, ".fd-infor .fdi-view")
         return views_string.split()[0].replace(",", "") if views_string else ""
 
     @return_on_error([])
     def __get_langs(self, node: Node) -> list:
-        langs_string = get_text(node, ".fd-infor > span:nth-child(1)")
+        langs_string = self.scraper_helper.get_text(node, ".fd-infor > span:nth-child(1)")
         return [lang for lang in langs_string.split("/")] if langs_string else []
 
     @return_on_error("")
     def __get_chapters_volumes(self, node: Node, index: int) -> str:
-        data_string = get_text(node, f".d-block span:nth-child({index})")
+        data_string = self.scraper_helper.get_text(
+            node, f".d-block span:nth-child({index})"
+        )
         return data_string.split()[1] if data_string else ""
 
     @return_on_error([])
@@ -52,8 +57,8 @@ def __get_genres(self, node: Node) -> list:
     @return_on_error({})
     def __build_dict(self, node: Node) -> dict:
         manga_dict = {
-            "rank": get_text(node, ".ranking-number span"),
-            "title": get_text(node, ".manga-detail .manga-name a"),
+            "rank": self.scraper_helper.get_text(node, ".ranking-number span"),
+            "title": self.scraper_helper.get_text(node, ".manga-detail .manga-name a"),
             "slug": self.__get_slug(node),
             "cover": self.__get_cover(node),
             "views": self.__get_views(node),

app/api/scrapers/popular.py

@@ -1,7 +1,7 @@
 from selectolax.parser import Node
 
 from app.api.decorators.return_decorator import return_on_error
-from ..utils import get_attribute, get_text
+from app.api.helpers.scraper import ScrapeHelper
 from ..helpers.html_helper import HTMLHelper
 
 
@@ -10,25 +10,23 @@ def __init__(self) -> None:
         url = "https://mangareader.to/home"
         # Facades
         self.html_helper = HTMLHelper()
+        self.scraper_helper = ScrapeHelper()
         # Parser
         self.parser = self.html_helper.get_parser(url)
 
-    @staticmethod
     @return_on_error("")
-    def __get_slug(node: Node) -> str:
-        slug = get_attribute(node, "a.link-mask", "href")
+    def __get_slug(self, node: Node) -> str:
+        slug = self.scraper_helper.get_attribute(node, "a.link-mask", "href")
         return slug.replace("/", "") if slug else ""
 
-    @staticmethod
     @return_on_error([])
-    def __get_langs(node: Node) -> list:
-        langs = get_text(node, ".mp-desc p:nth-of-type(3)")
+    def __get_langs(self, node: Node) -> list:
+        langs = self.scraper_helper.get_text(node, ".mp-desc p:nth-of-type(3)")
         return langs.split("/") if langs else []
 
-    @staticmethod
     @return_on_error({})
-    def __get_chapters_volumes(node: Node, index: int) -> dict:
-        data = get_text(node, f".mp-desc p:nth-of-type({index})")
+    def __get_chapters_volumes(self, node: Node, index: int) -> dict:
+        data = self.scraper_helper.get_text(node, f".mp-desc p:nth-of-type({index})")
         if data:
             total = data.split()[1]
             lang = data.split()[2].translate(str.maketrans("", "", "[]"))
@@ -41,11 +39,11 @@ def __get_chapters_volumes(node: Node, index: int) -> dict:
     @return_on_error({})
     def __build_dict(self, node) -> dict:
         manga_dict = {
-            "rank": get_text(node, ".number span"),
-            "title": get_text(node, ".anime-name"),
+            "rank": self.scraper_helper.get_text(node, ".number span"),
+            "title": self.scraper_helper.get_text(node, ".anime-name"),
             "slug": self.__get_slug(node),
-            "cover": get_attribute(node, "img.manga-poster-img", "src"),
-            "rating": get_text(node, ".mp-desc p:nth-of-type(2)"),
+            "cover": self.scraper_helper.get_attribute(node, "img.manga-poster-img", "src"),
+            "rating": self.scraper_helper.get_text(node, ".mp-desc p:nth-of-type(2)"),
             "langs": self.__get_langs(node),
             "chapters": self.__get_chapters_volumes(node, 4),
             "volumes": self.__get_chapters_volumes(node, 5),

app/api/scrapers/topten.py

@@ -1,7 +1,7 @@
 from selectolax.parser import Node
 
 from app.api.decorators.return_decorator import return_on_error
-from ..utils import get_text, get_attribute
+from app.api.helpers.scraper import ScrapeHelper
 from ..helpers.html_helper import HTMLHelper
 
 
@@ -10,19 +10,18 @@ def __init__(self) -> None:
         url = "https://mangareader.to/home"
         # Facades
         self.html_helper = HTMLHelper()
+        self.scraper_helper = ScrapeHelper()
         # Parser
         self.parser = self.html_helper.get_parser(url)
 
-    @staticmethod
     @return_on_error("")
-    def __get_slug(node: Node) -> str:
-        slug = get_attribute(node, ".desi-head-title a", "href")
+    def __get_slug(self, node: Node) -> str:
+        slug = self.scraper_helper.get_attribute(node, ".desi-head-title a", "href")
         return slug.replace("/", "") if slug else ""
 
-    @staticmethod
     @return_on_error({})
-    def __get_chapters(node: Node) -> dict:
-        chapters_string = get_text(node, ".desi-sub-text")
+    def __get_chapters(self, node: Node) -> dict:
+        chapters_string = self.scraper_helper.get_text(node, ".desi-sub-text")
         if chapters_string:
             total = chapters_string.split()[1]
             lang = chapters_string.split()[2].translate(str.maketrans("", "", "[]"))
@@ -41,10 +40,10 @@ def __get_genres(node: Node) -> list:
     @return_on_error({})
     def __build_dict(self, node: Node) -> dict:
         manga_dict = {
-            "title": get_text(node, ".desi-head-title a"),
+            "title": self.scraper_helper.get_text(node, ".desi-head-title a"),
             "slug": self.__get_slug(node),
-            "cover": get_attribute(node, "img.manga-poster-img", "src"),
-            "synopsis": get_text(node, ".sc-detail .scd-item"),
+            "cover": self.scraper_helper.get_attribute(node, "img.manga-poster-img", "src"),
+            "synopsis": self.scraper_helper.get_text(node, ".sc-detail .scd-item"),
             "chapters": self.__get_chapters(node),
             "genres": self.__get_genres(node),
         }