Fixes source teanovel.com

sources/en/t/teanovel.py

@@ -11,7 +11,12 @@
 
 
 class TeaNovelCrawler(Crawler):
-    base_url = ["https://www.teanovel.com/", "https://www.teanovel.net/"]
+    base_url = "https://www.teanovel.com"
+
+    def initialize(self):
+        self.init_executor(
+            workers=4
+        )
 
     def read_novel_info(self):
         soup = self.get_soup(self.novel_url)
@@ -22,40 +27,26 @@ def read_novel_info(self):
 
         next_data = json.loads(script_tag.get_text())
 
-        build_id = next_data["buildId"]
-        novel_data = next_data["props"]["pageProps"]["novelData"]["novel"]
+        novel_data = next_data["props"]["pageProps"]["novel"]
 
         self.novel_title = novel_data["name"]
         self.novel_author = novel_data["author"]
 
-        # img_tag = soup.select_one("main img[src*='_next/']")
-        # if isinstance(img_tag, Tag):
-        #     self.novel_cover = self.absolute_url(img_tag["src"])
-
-        slug = novel_data["slug"]
-
-        toc_url = f"{self.home_url}api/chapters/{slug}?slug={slug}&orderBy=asc"
-        toc_json = self.get_json(toc_url)
-
-        while True:
-            for chapter in toc_json["data"]:
-                chapter_id = len(self.chapters) + 1
-                self.chapters.append(
-                    {
-                        "id": chapter_id,
-                        "title": f"Chapter {chapter_id}: {chapter['title']}",
-                        "url": (
-                            f"{self.home_url}_next/data/{build_id}/novel/{slug}/{chapter['slug']}.json"
-                        ),
-                    }
-                )
-            if "nextId" in toc_json:
-                toc_json = self.get_json(toc_url + f"&nextId={toc_json['nextId']}")
-            else:
-                break
+        img_tag = soup.select_one("main img[src*='_next/']")
+        if isinstance(img_tag, Tag):
+            self.novel_cover = self.absolute_url(img_tag["src"])
+
+        chapters = self.get_soup(self.novel_url + "/chapter-list").select("a.border-b")
+        for chapter in chapters:
+            chapter_id = len(self.chapters) + 1
+            self.chapters.append(
+                {
+                    "id": chapter_id,
+                    "title": chapter.select_one("p").get_text(strip=True),
+                    "url": self.absolute_url(chapter["href"]),
+                }
+            )
 
     def download_chapter_body(self, chapter):
-        chapter_json = self.get_json(chapter["url"])
-        chapter_data = chapter_json["pageProps"]["chapterData"]
-
-        return chapter_data["content"].replace("\n", "<br>")
+        chapter = self.get_soup(chapter["url"])
+        return self.cleaner.extract_contents(chapter.select_one("div.prose"))