Redirect mangakakalot/broken manganelo links to migrated url

1 files changed, 56 insertions, 1 deletions

diff --git a/plugins/manganelo.py b/plugins/manganelo.py
index 312d093..4427334 100755
--- a/plugins/manganelo.py
+++ b/plugins/manganelo.py
@@ -8,6 +8,10 @@ import json
 
 from lxml import etree
 
+headers = {
+    'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36"
+}
+
 def usage():
     print("manganelo.py command")
     print("commands:")
@@ -54,8 +58,51 @@ def download_file(url, save_path):
                     file_size += len(chunk)
     return file_size
 
+def redirect_check(response_text, url):
+    idx = response_text.find('window.location.assign("')
+    if idx == -1:
+        return (response_text, url)
+
+    idx += 24
+    end = response_text.find('"', idx)
+    if end == -1:
+        return (response_text, url)
+
+    response = requests.get(response_text[idx:end], timeout=30, headers=headers)
+    response.raise_for_status()
+    return (response.text, response.url)
+
+def redirect_migrated_url(url, tree, is_chapter):
+    for element in tree.xpath('//div[@class="panel-not-found"]'):
+        if url[-1] == '/':
+            url = url[:-1]
+
+        url = url.replace("manganelo", "mangakakalot")
+        chapter = None
+        if is_chapter:
+            idx = url.rfind('/')
+            if idx == -1:
+                print("Chapter not found in url")
+                return None
+            chapter = url[idx + 1:]
+            url = url[0:idx]
+
+        response = requests.get(url, timeout=30, headers=headers)
+        response.raise_for_status()
+
+        text, url = redirect_check(response.text, url)
+        if chapter:
+            url = url + "/" + chapter
+            response = requests.get(url, timeout=30, headers=headers)
+            response.raise_for_status()
+            text = response.text
+
+        return etree.HTML(text)
+
+    return tree
+
 def list_chapters(url, chapter_list_input):
-    response = requests.get(url, timeout=30)
+    response = requests.get(url, timeout=30, headers=headers)
     response.raise_for_status()
 
     seen_titles = set()
@@ -71,6 +118,8 @@ def list_chapters(url, chapter_list_input):
             seen_urls.add(chapter_url.replace("mangakakalot", "manganelo"))
 
     tree = etree.HTML(response.text)
+    tree = redirect_migrated_url(url, tree, False)
+
     chapters = []
     for element in tree.xpath('//ul[@class="row-content-chapter"]//a'):
         element_text = element.text.strip().replace("/", "_")
@@ -89,6 +138,11 @@ def download_chapter(url, download_dir):
         file.write(url)
 
     tree = etree.HTML(response.text)
+    tree = redirect_migrated_url(url, tree, True)
+    if tree is None:
+        os.remove(in_progress_filepath)
+        exit(2)
+
     img_number = 1
     for image_source in tree.xpath('//div[@class="container-chapter-reader"]/img/@src'):
         ext = image_source[image_source.rfind("."):]
@@ -127,6 +181,7 @@ if command == "list":
 elif command == "download":
     if len(sys.argv) < 4:
         usage_download()
+
     url = sys.argv[2].replace("mangakakalot", "manganelo")
     download_dir = sys.argv[3]
     download_chapter(url, download_dir)