Merge pull request #2 from jere344/patch-2

Update novelsemperor.py

sources/en/n/novelsemperor.py

@@ -1,13 +1,13 @@
 # -*- coding: utf-8 -*-
 import logging
 import re
-from lncrawl.templates.mangastream import MangaStreamTemplate
+from lncrawl.core.crawler import Crawler
 
 logger = logging.getLogger(__name__)
-search_url = 'https://novelsemperor.com/series?title=%s&type=&status='
+search_url = "https://novelsemperor.com/series?title=%s&type=&status="
 
 
-class NovelsEmperorCrawler(MangaStreamTemplate):
+class NovelsEmperorCrawler(Crawler):
     base_url = ["https://novelsemperor.com/"]
 
     def initialize(self) -> None:
@@ -26,7 +26,7 @@ def search_novel(self, query):
         results = []
         for tab in soup.select("div.xlg\\:grid-cols-8.grid.grid-cols-3 div#card-real"):
             a = tab.select_one("a")
-            title = a["href"][33:].replace('-', ' ')
+            title = a["href"][33:].replace("-", " ")
             img = tab.select_one("img")["data-src"]
             results.append(
                 {
@@ -41,55 +41,61 @@ def search_novel(self, query):
     def read_novel_info(self):
         logger.debug("Visiting %s", self.novel_url)
         pagination_num = self.get_soup(self.novel_url)
-        pagination_num = pagination_num.select_one("ul > li:nth-last-child(2)").text
-        pagination_num = int(pagination_num)
-
-        soup = []
+        pagination_num = pagination_num.select_one("ul > li:nth-last-child(2)")
+
+        if pagination_num:
+            pagination_num = pagination_num["onclick"]
+            # We match page={number} from the link and then extract the number
+            regex = re.compile(r"page=\d+")
+            pagination_num = regex.findall(pagination_num)[0].split("=")[1]
+            pagination_num = int(pagination_num)
+        else:
+            pagination_num = 1
 
-        for i in range(1, pagination_num + 1):
-            soup.append(self.get_soup(f'{self.novel_url}?page={i}'))
+        futures = [
+            self.executor.submit(self.get_soup, f"{self.novel_url}?page={i}")
+            for i in range(1, pagination_num + 1)
+        ]
+        page_soups = [f.result() for f in futures]
 
-        possible_title = soup[0].select_one("h2.text-2xl")
+        possible_title = page_soups[0].select_one("h2.text-2xl")
         assert possible_title, "No novel title"
+        text_sm = possible_title.select_one("span")
+        if text_sm:
+            text_sm.extract()
+        self.novel_title = possible_title.text.strip()
         logger.info("Novel title: %s", self.novel_title)
 
-        author = soup[0].select('p:nth-child(4) > span.capitalize')
+        author = page_soups[0].select("p:nth-child(4) > span.capitalize")
         if len(author) == 2:
             self.novel_author = author[0].text + " (" + author[1].text + ")"
-        else:
+        elif author[0].text != "-":
             self.novel_author = author[0].text
         logger.info("Novel author: %s", self.novel_author)
 
         self.novel_cover = self.absolute_url(
-            soup[0].select_one("div.relative > img")["src"]
+            page_soups[0].select_one("div.relative > img")["src"]
         )
         logger.info("Novel cover: %s", self.novel_cover)
 
-        for i in range(len(soup) - 1, -1, -1):
-            for div in soup[i].select("div#chapters-list"):
-                vol_title = div.select_one("a div div span").text
-                vol_id = [int(x) for x in re.findall(r"\d+", vol_title)]
-                vol_id = vol_id[0] if len(vol_id) else len(self.volumes) + 1
-                self.volumes.append(
-                    {
-                        "id": vol_id,
-                        "title": vol_title,
-                    }
-                )
-
-                for a in div.select("a"):
-                    ch_title = a.select_one("div div span").text
-                    ch_id = [int(x) for x in re.findall(r"\d+", ch_title)]
-                    ch_id = ch_id[0] if len(ch_id) else len(self.chapters) + 1
-                    self.chapters.append(
-                        {
-                            "id": ch_id,
-                            "volume": vol_id,
-                            "title": ch_title,
-                            "url": self.absolute_url(a["href"]),
-                        }
-                    )
-
+        # [sp.select("div#chapters-list a") for sp in soup]
+        # flattened ->
+        # [a for sp in soup for a in sp.select("div#chapters-list a")])
+        for element in reversed(
+            [a for soup in page_soups for a in soup.select("div#chapters-list a")]
+        ):
+            ch_id = len(self.chapters) + 1
+            vol_id = len(self.chapters) // 100 + 1
+            if len(self.chapters) % 100 == 0:
+                self.volumes.append({"id": vol_id})
+            self.chapters.append(
+                {
+                    "id": ch_id,
+                    "volume": vol_id,
+                    "title": element.select_one("div div span").text,
+                    "url": self.absolute_url(element["href"]),
+                }
+            )
         logger.debug(
             "%d chapters and %d volumes found", len(self.chapters), len(self.volumes)
         )