Removes unnecesary logs

dipu-bd · Jan 8, 2025 · 3795b66 · 3795b66
1 parent 6956d28
commit 3795b66
Show file tree

Hide file tree

Showing 5 changed files with 46 additions and 42 deletions.
diff --git a/sources/en/d/dobelyuwai.py b/sources/en/d/dobelyuwai.py
@@ -29,12 +29,6 @@ def read_novel_info(self):
             self.novel_cover = None
         logger.info("Novel cover: %s", self.novel_cover)
 
-        # try:
-        #     self.novel_author = soup.select_one('div.entry-content > p:nth-child(2)').text.strip()
-        # except Exception as e:
-        #     logger.warning('Failed to get novel auth. Error: %s', e)
-        # logger.info('%s', self.novel_author)
-
         # Removes none TOC links from bottom of page.
         toc_parts = soup.select_one("div.entry-content")
 

diff --git a/sources/en/n/novelhall.py b/sources/en/n/novelhall.py
@@ -23,10 +23,10 @@ def search_novel(self, query: str):
         soup = self.get_soup(self.absolute_url(search_url + quote_plus(query.lower())))
 
         results = []
-        for novel in soup.select('.section3 table tbody tr'):
-            novel = novel.findAll('a')
+        for novel in soup.select(".section3 table tbody tr"):
+            novel = novel.findAll("a")
             novel_link = novel[1]
-            latest_chapter = novel[2].text.strip().split('.')
+            latest_chapter = novel[2].text.strip().split(".")
             chapter_number = latest_chapter[0]
 
             if chapter_number.isdigit():
@@ -37,8 +37,8 @@ def search_novel(self, query: str):
             results.append(
                 {
                     "title": novel_link.text.strip(),
-                    "url": self.absolute_url(novel_link['href']),
-                    "info": latest_chapter
+                    "url": self.absolute_url(novel_link["href"]),
+                    "info": latest_chapter,
                 }
             )
 
@@ -60,20 +60,16 @@ def read_novel_info(self):
         possible_image = soup.select_one("div.book-img img")
         if possible_image:
             self.novel_cover = self.absolute_url(possible_image["src"])
-
-            if possible_image['src'] == "":
-                logger.warning("Novel cover: unavailable")
-            else:
-                logger.info("Novel cover: %s", self.novel_cover)
-        else:
-            logger.info("Novel cover: unavailable")
+        logger.info("Novel cover: %s", self.novel_cover)
 
         author = soup.select("div.book-info div.total.booktag span.blue")[0]
         author.select_one("p").extract()
         self.novel_author = author.text.replace("Author：", "").strip()
         logger.info("Novel author: %s", self.novel_author)
 
-        self.novel_tags = [soup.select_one("div.book-info div.total.booktag a.red").text.strip()]
+        self.novel_tags = [
+            soup.select_one("div.book-info div.total.booktag a.red").text.strip()
+        ]
         logger.info("Novel tags: %s", self.novel_tags)
 
         synopsis = soup.select_one(".js-close-wrap")

diff --git a/sources/en/n/novelight.py b/sources/en/n/novelight.py
@@ -21,7 +21,9 @@ def initialize(self) -> None:
         self.cleaner.bad_css.update(["div.advertisment"])
 
     def search_novel(self, query) -> List[SearchResult]:
-        soup = self.get_soup(f"{self.home_url}catalog/?search={quote_plus(query.lower())}")
+        soup = self.get_soup(
+            f"{self.home_url}catalog/?search={quote_plus(query.lower())}"
+        )
 
         return [
             SearchResult(title=a.text.strip(), url=self.absolute_url(a["href"]))
@@ -47,7 +49,9 @@ def read_novel_info(self):
         if isinstance(novel_synopsis, Tag):
             self.novel_synopsis = self.cleaner.extract_contents(novel_synopsis)
 
-        novel_tags = soup.select("div#information section.tags a[href^='/catalog/?tags=']")
+        novel_tags = soup.select(
+            "div#information section.tags a[href^='/catalog/?tags=']"
+        )
         for tag in novel_tags:
             self.novel_tags.append(tag.get_text().strip())
 
@@ -57,27 +61,27 @@ def read_novel_info(self):
         logger.info("Novel author: %s", self.novel_author)
 
         page_scripts = soup.select("body > script:not([src])")
-        scripts_joined = '\n'.join(str(s) for s in page_scripts)
+        scripts_joined = "\n".join(str(s) for s in page_scripts)
         book_id = re.search(r'.*const BOOK_ID = "(\d+)".*', scripts_joined).group(1)
         if not book_id:
             raise LNException("Could not extract book_id from novel page")
         logger.debug("book_id: %s", book_id)
         # this is different token than the 'csrftoken' in cookies
-        csrfmiddlewaretoken = re.search(r'.*window.CSRF_TOKEN = "(\w+)".*', scripts_joined).group(1)
+        csrfmiddlewaretoken = re.search(
+            r'.*window.CSRF_TOKEN = "(\w+)".*', scripts_joined
+        ).group(1)
         if not csrfmiddlewaretoken:
             raise LNException("Could not extract csrfmiddlewaretoken from novel page")
         logger.debug("csrfmiddlewaretoken: %s", csrfmiddlewaretoken)
 
         headers = {
             "Accept": "*/*",
             "Referer": self.novel_url,
-            "x-requested-with": "XMLHttpRequest"
+            "x-requested-with": "XMLHttpRequest",
         }
         chapters_lists = soup.select("select#select-pagination-chapter > option")
         bar = self.progress_bar(
-            total=len(chapters_lists),
-            desc="Chapters list",
-            unit="page"
+            total=len(chapters_lists), desc="Chapters list", unit="page"
         )
         encountered_paid_chapter = False
         for page in reversed(chapters_lists):
@@ -86,11 +90,11 @@ def read_novel_info(self):
             params = {
                 "csrfmiddlewaretoken": csrfmiddlewaretoken,
                 "book_id": book_id,
-                "page": page["value"]
+                "page": page["value"],
             }
             chapters_response = self.get_json(
                 f"{self.home_url}book/ajax/chapter-pagination?{urlencode(params)}",
-                headers=headers
+                headers=headers,
             )
             chapters_soup = self.make_soup(chapters_response["html"])
             for a in reversed(chapters_soup.select("a[href^='/book/chapter/']")):
@@ -108,7 +112,9 @@ def read_novel_info(self):
             bar.update()
         bar.close()
         if encountered_paid_chapter:
-            logger.warning("WARNING: Paid chapters are not supported and will be skipped.")
+            logger.warning(
+                "WARNING: Paid chapters are not supported and will be skipped."
+            )
 
     def download_chapter_body(self, chapter: Chapter):
         soup = self.get_soup(chapter.url)

diff --git a/sources/zh/ddxsss.py b/sources/zh/ddxsss.py
@@ -22,10 +22,12 @@ def initialize(self):
         # the default lxml parser cannot handle the huge gbk encoded sites (fails after 4.3k chapters)
         self.init_parser("html.parser")
         self.cleaner.bad_tags.update(["script", "a"])
-        self.cleaner.bad_css.update([
-            ".noshow",
-            "div.Readpage.pagedown",
-        ])
+        self.cleaner.bad_css.update(
+            [
+                ".noshow",
+                "div.Readpage.pagedown",
+            ]
+        )
 
         # p tags should only show up after being parsed and formatted the first time
         self.cleaner.bad_tag_text_pairs["p"] = [
@@ -44,10 +46,10 @@ def search_novel(self, query):
         data = self.get_json(
             f"{self.home_url}user/search.html?q={query}",
             # if this cookie "expires" it might return INT results again -> maybe remove search functionality
-            cookies={"hm": "7c2cee175bfbf597f805ebc48957806e"}
+            cookies={"hm": "7c2cee175bfbf597f805ebc48957806e"},
         )
         if isinstance(data, int):
-            logger.warning("Failed to get any results, likely auth failure")
+            logger.info("Failed to get any results, likely auth failure")
             return []
 
         results = []
@@ -56,7 +58,7 @@ def search_novel(self, query):
                 SearchResult(
                     title=book["articlename"],
                     url=self.absolute_url(book["url_list"]),
-                    info=f"Author: {book['author']} | Synopsis: {book['intro']}"
+                    info=f"Author: {book['author']} | Synopsis: {book['intro']}",
                 )
             )
         return results
@@ -78,7 +80,7 @@ def read_novel_info(self):
             self.novel_cover = self.absolute_url(possible_image["src"])
         logger.info("Novel cover: %s", self.novel_cover)
 
-        possible_author = meta.find('.small span', text=r"作者：")
+        possible_author = meta.find(".small span", text=r"作者：")
         if isinstance(possible_author, Tag):
             self.novel_author = possible_author.text.strip().replace("作者：", "")
         logger.info("Novel Author: %s", self.novel_author)
@@ -96,13 +98,15 @@ def read_novel_info(self):
                 logger.info("Skipping non-chapter link: %s", a["href"])
                 continue
 
-            chap_id = int(re.match(re.compile(f".*/book/{book_id}/(\\d+).*"), a["href"])[1])
+            chap_id = int(
+                re.match(re.compile(f".*/book/{book_id}/(\\d+).*"), a["href"])[1]
+            )
             vol_id = len(self.chapters) // 100 + 1
             if len(self.chapters) % 100 == 0:
                 self.volumes.append(Volume(vol_id))
             if not a:
                 # this should not occur with html.parser, if it does, likely due to parser/encoding issue
-                logger.warning("Failed to get Chapter %d! Missing Link", chap_id)
+                logger.info("Failed to get Chapter %d! Missing Link", chap_id)
                 continue
             self.chapters.append(
                 Chapter(

diff --git a/sources/zh/uukanshu.py b/sources/zh/uukanshu.py
@@ -46,7 +46,9 @@ def read_novel_info(self) -> None:
                 self.novel_synopsis = synopsis.select_one("p").text
 
         chapters = soup.select_one("ul#chapterList")
-        for chapter in list(chapters.children)[::-1]:  # reverse order as it's newest to oldest
+        for chapter in list(chapters.children)[
+            ::-1
+        ]:  # reverse order as it's newest to oldest
             # convince typehint that we're looking at Tags & also make sure we skip random text within the ul if any
             if not isinstance(chapter, Tag):
                 continue
@@ -61,7 +63,9 @@ def read_novel_info(self) -> None:
                 continue
             anchor = chapter.select_one("a")
             if not anchor:
-                logger.warning("Found <li> in chapter list, not volume, without link: %s", chapter)
+                logger.info(
+                    "Found <li> in chapter list, not volume, without link: %s", chapter
+                )
                 continue
             self.chapters.append(
                 Chapter(