Merge pull request #1148 from dipu-bd/dev

Version 2.28.9

README.md

@@ -209,7 +209,7 @@ $ lncrawl -h
 ┃┃╱╭╋┫╭╮┃╭╮┃┃┃╭╮┫╭╮┃╰╯┃┃━┫┃╱┃┃╱╭┫╭┫╭╮┃╰╯╰╯┃┃┃┃━┫╭╯
 ┃╰━╯┃┃╰╯┃┃┃┃╰┫┃┃┃╰╯┣╮╭┫┃━┫╰╮┃╰━╯┃┃┃╭╮┣╮╭╮╭┫╰┫┃━┫┃
 ╰━━━┻┻━╮┣╯╰┻━┻╯╰┻━━╯╰╯╰━━┻━╯╰━━━┻╯╰╯╰╯╰╯╰╯╰━┻━━┻╯
-╱╱╱╱╱╭━╯┃ v2.28.8
+╱╱╱╱╱╭━╯┃ v2.28.9
 ╱╱╱╱╱╰━━╯ 🔗 https://github.com/dipu-bd/lightnovel-crawler
 --------------------------------------------------------------------------------
 usage: lncrawl [options...]
@@ -1147,12 +1147,12 @@ We are supporting 203 sources and 221 crawlers.
 </tr>
 <tr><td><span title="Contains machine translations"></span><span title="Supports searching">🔍</span><span title="Supports login"></span><span title="Contains manga/manhua/manhwa"></span></td>
 <td><a href="https://www.lightnovelpub.com/" target="_blank">https://www.lightnovelpub.com/</a></td>
-<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/l/lightnovelpub.py" title="01 October 2021 04:52:32 AM">11</a></td>
+<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/l/lightnovelpub.py" title="15 October 2021 02:14:01 AM">12</a></td>
 <td><a href="https://github.com/dipu-bd"><img src="https://avatars.githubusercontent.com/u/5158124?v=4&s=24" alt="dipu-bd" height="24"/></a> <a href="https://github.com/SirGryphin"><img src="https://avatars.githubusercontent.com/u/36343615?v=4&s=24" alt="SirGryphin" height="24"/></a> <a href="https://github.com/Galunid"><img src="https://avatars.githubusercontent.com/u/10298730?v=4&s=24" alt="Galunid" height="24"/></a></td>
 </tr>
 <tr><td><span title="Contains machine translations"></span><span title="Supports searching">🔍</span><span title="Supports login"></span><span title="Contains manga/manhua/manhwa"></span></td>
 <td><a href="https://www.lightnovelworld.com/" target="_blank">https://www.lightnovelworld.com/</a></td>
-<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/l/lightnovelpub.py" title="01 October 2021 04:52:32 AM">11</a></td>
+<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/l/lightnovelpub.py" title="15 October 2021 02:14:01 AM">12</a></td>
 <td><a href="https://github.com/dipu-bd"><img src="https://avatars.githubusercontent.com/u/5158124?v=4&s=24" alt="dipu-bd" height="24"/></a> <a href="https://github.com/SirGryphin"><img src="https://avatars.githubusercontent.com/u/36343615?v=4&s=24" alt="SirGryphin" height="24"/></a> <a href="https://github.com/Galunid"><img src="https://avatars.githubusercontent.com/u/10298730?v=4&s=24" alt="Galunid" height="24"/></a></td>
 </tr>
 <tr><td><span title="Contains machine translations"></span><span title="Supports searching">🔍</span><span title="Supports login"></span><span title="Contains manga/manhua/manhwa"></span></td>
@@ -1237,8 +1237,8 @@ We are supporting 203 sources and 221 crawlers.
 </tr>
 <tr><td><span title="Contains machine translations"></span><span title="Supports searching"></span><span title="Supports login"></span><span title="Contains manga/manhua/manhwa"></span></td>
 <td><a href="https://www.oppatranslations.com/" target="_blank">https://www.oppatranslations.com/</a></td>
-<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/o/oppatranslations.py" title="27 July 2021 10:03:56 PM">4</a></td>
-<td><a href="https://github.com/dipu-bd"><img src="https://avatars.githubusercontent.com/u/5158124?v=4&s=24" alt="dipu-bd" height="24"/></a> <a href="https://github.com/amritoo"><img src="https://avatars.githubusercontent.com/u/45586379?v=4&s=24" alt="amritoo" height="24"/></a></td>
+<td><a href="https://github.com/dipu-bd/lightnovel-crawler/blob/master/sources/en/o/oppatrans.py" title="16 July 2021 02:11:58 PM">61</a></td>
+<td><a href="https://github.com/dipu-bd"><img src="https://avatars.githubusercontent.com/u/5158124?v=4&s=24" alt="dipu-bd" height="24"/></a> <a href="https://github.com/SirGryphin"><img src="https://avatars.githubusercontent.com/u/36343615?v=4&s=24" alt="SirGryphin" height="24"/></a> <a href="https://github.com/yudilee"><img src="https://avatars.githubusercontent.com/u/7065691?v=4&s=24" alt="yudilee" height="24"/></a> <a href="https://github.com/AncientCatz"><img src="https://avatars.githubusercontent.com/u/69200720?v=4&s=24" alt="AncientCatz" height="24"/></a></td>
 </tr>
 <tr><td><span title="Contains machine translations"></span><span title="Supports searching"></span><span title="Supports login"></span><span title="Contains manga/manhua/manhwa"></span></td>
 <td><a href="https://www.ornovel.com/" target="_blank">https://www.ornovel.com/</a></td>

lncrawl/VERSION

@@ -1 +1 @@
-2.28.8
+2.28.9

lncrawl/binders/epub.py

@@ -18,8 +18,8 @@ def make_cover_image(app):
     logger.info('Creating cover: %s', app.book_cover)
     # ext = app.book_cover.split('.')[-1]
     cover_image = epub.EpubImage()
-    cover_image.file_name = 'cover.png'
-    cover_image.media_type = 'image/png'
+    cover_image.file_name = 'cover.jpg'
+    cover_image.media_type = 'image/jpeg'
     with open(app.book_cover, 'rb') as image_file:
         cover_image.content = image_file.read()
     # end with
@@ -154,7 +154,7 @@ def bind_epub_book(app, chapters, volume=''):
 
     # Create book spine
     try:
-        book.set_cover('book-cover.png', open(app.book_cover, 'rb').read())
+        book.set_cover('book-cover.jpg', open(app.book_cover, 'rb').read())
         book.spine = ['cover', intro_page, 'nav']
     except Exception:
         book.spine = [intro_page, 'nav']

lncrawl/core/downloader.py

@@ -30,15 +30,15 @@ def download_image(app, url) -> Image.Image:
 
 def download_cover(app):
     filename = None
-    filename = os.path.join(app.output_path, 'cover.png')
+    filename = os.path.join(app.output_path, 'cover.jpg')
     if os.path.exists(filename):
         return filename
 
     logger.info('Downloading original cover image...')
     image_url = app.crawler.novel_cover
     try:
         img = download_image(app, image_url)
-        img.save(filename, 'PNG')
+        img.convert('RGB').save(filename, "JPEG")
         logger.debug('Saved cover: %s', filename)
         return filename
     except Exception as ex:
@@ -47,10 +47,10 @@ def download_cover(app):
     # end try
 
     logger.info('Downloading fallback cover image...')
-    image_url = 'https://source.unsplash.com/featured/1200x1550?abstract'
+    image_url = 'https://source.unsplash.com/featured/800x1032?abstract'
     try:
         img = download_image(app, image_url)
-        img.save(filename, 'PNG')
+        img.convert('RGB').save(filename, "JPEG")
         logger.debug('Saved cover: %s', filename)
         return filename
     except Exception as ex:

sources/en/l/lightnovelpub.py

@@ -1,9 +1,9 @@
 # -*- coding: utf-8 -*-
 import logging
 import re
-from urllib.parse import urlparse
 
 from bs4.element import Tag
+
 from lncrawl.core.crawler import Crawler
 
 logger = logging.getLogger(__name__)
@@ -25,10 +25,12 @@ def search_novel(self, query):
         results = []
         for a in soup.select('.novel-list .novel-item a'):
             assert isinstance(a, Tag)
+            possible_info = a.select_one('.novel-stats')
+            info = possible_info.text.strip() if isinstance(possible_info, Tag) else None
             results.append({
                 'title': str(a['title']).strip(),
                 'url': self.absolute_url(a['href']),
-                'info': a.select_one('.novel-stats').text.strip(),
+                'info': info,
             })
         # end for
         return results
@@ -40,22 +42,19 @@ def read_novel_info(self):
         logger.debug('Visiting %s', self.novel_url)
         soup = self.get_soup(self.novel_url)
 
-        self.novel_title = soup.select_one('.novel-info .novel-title').text.strip()
+        possible_title = soup.select_one('.novel-info .novel-title')
+        assert isinstance(possible_title, Tag)
+        self.novel_title = possible_title.text.strip()
         logger.info('Novel title: %s', self.novel_title)
 
-        try:
-            self.novel_cover = self.absolute_url(
-                soup.select_one('.glass-background img')['src'])
-        except Exception as err:
-            logger.debug('Failed to parse novel cover. Error: %s', err)
-        # end try
+        possible_image = soup.select_one('.glass-background img')
+        if isinstance(possible_image, Tag):
+            self.novel_cover = self.absolute_url(possible_image['src'])
         logger.info('Novel cover: %s', self.novel_cover)
 
-        try:
-            self.novel_author = soup.select_one('.author a[href*="/author/"]')['title']
-        except Exception as err:
-            logger.debug('Failed to parse novel author. Error: %s', err)
-        # end try
+        possible_author = soup.select_one('.author a[href*="/author/"]')
+        if isinstance(possible_author, Tag):
+            self.novel_author = possible_author['title']
         logger.info('Novel author: %s', self.novel_author)
 
         logger.info('Getting chapters...')