Merge pull request #29 from SenZmaKi/v2.1.4

V2.1.4

.gitignore

@@ -12,4 +12,5 @@ marin.py
 setups
 build
 dist
+.scraps/
 crap.py

bump_version.py

@@ -0,0 +1,56 @@
+from io import TextIOWrapper
+import os
+import subprocess
+
+PREV_VERSION = "2.1.3"
+NEW_VERSION = "2.1.4"
+FILES_PATHS = [
+    "pyproject.toml",
+    "senpwai/utils/static.py",
+    "setup.iss",
+    "setup_senpcli.iss",
+]
+
+
+def log_error(msg: str) -> None:
+    print(f"[-] Error: {msg}")
+
+
+def log_info(msg: str) -> None:
+    print(f"[+] Info: {msg}")
+
+
+def log_warning(msg: str) -> None:
+    print(f"[!] Warning: {msg}")
+
+
+def truncate(file: TextIOWrapper, content: str) -> None:
+    file.seek(0)
+    file.write(content)
+    file.truncate()
+
+
+def main() -> None:
+    log_info(f"Bumping version from {PREV_VERSION} -> {NEW_VERSION}\n")
+    for file_path in FILES_PATHS:
+        if not os.path.isfile(file_path):
+            log_error(f'"{file_path}" not found')
+            continue
+        with open(file_path, "r+") as f:
+            content = f.read()
+            new_content = content.replace(PREV_VERSION, NEW_VERSION)
+            if new_content == content:
+                if NEW_VERSION in new_content:
+                    log_warning(
+                        f'Failed to find previous version in "{file_path}" but the new version is in it'
+                    )
+                else:
+                    log_error(f'Failed to find previous version in "{file_path}"')
+                continue
+            truncate(f, new_content)
+            log_info(f'Bumped version in "{file_path}"')
+    subprocess.run("git diff")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "senpwai"
-version = "2.1.3"
+version = "2.1.4"
 description = "A desktop app for tracking and batch downloading anime"
 authors = ["SenZmaKi <[email protected]>"]
 license = "GPL v3"
@@ -9,7 +9,7 @@ include = ["senpwai/assets"]
 packages = [{ include = "senpwai" }, { include = "senpcli", from = "senpwai" }]
 exclude = ["src/**/test.py"]
 repository = "https://github.com/SenZmaKi/Senpwai"
-documentation = "https://github.com/SenZmaKi/Senpwai/blob/master/docs"
+documentation = "https://github.com/SenZmaKi/Senpwai/blob/master/README.md"
 keywords = [
   "anime",
   "app",

senpwai/main.py

@@ -6,7 +6,7 @@
 from PyQt6.QtCore import QCoreApplication, Qt
 from PyQt6.QtGui import QPalette
 from PyQt6.QtWidgets import QApplication
-from senpwai.utils.static import APP_NAME, custom_exception_handler
+from senpwai.utils.static import APP_NAME, custom_exception_handler, OS
 from senpwai.windows.main import MainWindow
 
 
@@ -26,7 +26,7 @@ def windows_app_initialisation():
 
 
 def main():
-    if sys.platform == "win32":
+    if OS.is_windows:
         windows_app_initialisation()
 
     QCoreApplication.setApplicationName(APP_NAME)

senpwai/scrapers/gogo/__init__.py

@@ -1,3 +1,3 @@
-from .hls import * # noqa F403
-from .main import * # noqa F403
-from .constants import GOGO # noqa F401
+from .hls import *  # noqa F403
+from .main import *  # noqa F403
+from .constants import GOGO  # noqa F401

senpwai/scrapers/gogo/constants.py

@@ -2,9 +2,10 @@
 
 GOGO = "gogo"
 GOGO_HOME_URL = "https://anitaku.to"
-AJAX_SEARCH_URL = "https://ajax.gogo-load.com/site/loadAjaxSearch?keyword="
+AJAX_ENTRY_POINT = "https://ajax.gogocdn.net"
+AJAX_SEARCH_URL = f"{AJAX_ENTRY_POINT}/site/loadAjaxSearch?keyword="
 AJAX_LOAD_EPS_URL = (
-    "https://ajax.gogo-load.com/ajax/load-list-episode?ep_start={}&ep_end={}&id={}"
+    f"{AJAX_ENTRY_POINT}/ajax/load-list-episode?ep_start={{}}&ep_end={{}}&id={{}}"
 )
 FULL_SITE_NAME = "Gogoanime"
 DUB_EXTENSION = " (Dub)"

senpwai/scrapers/gogo/main.py

@@ -37,9 +37,13 @@ def search(keyword: str, ignore_dub=True) -> list[tuple[str, str]]:
     for a in a_tags:
         title = a.text
         link = f'{GOGO_HOME_URL}/{a["href"]}'
-        if DUB_EXTENSION in title and ignore_dub:
-            continue
         title_and_link.append((title, link))
+    for title, link in title_and_link:
+        if ignore_dub and DUB_EXTENSION in title:
+            sub_title = title.replace(DUB_EXTENSION, "")
+            if any([sub_title == title for title, _ in title_and_link]):
+                title_and_link.remove((title, link))
+
     return title_and_link
 
 
@@ -49,6 +53,10 @@ def extract_anime_id(anime_page_content: bytes) -> int:
     return int(anime_id)
 
 
+def title_is_dub(title: str) -> bool:
+    return DUB_EXTENSION in title
+
+
 def get_download_page_links(
     start_episode: int, end_episode: int, anime_id: int
 ) -> list[str]:
@@ -206,6 +214,6 @@ def get_session_cookies(fresh=False) -> RequestsCookieJar:
     # A valid User-Agent is required during this post request hence the CLIENT is technically only necessary here
     response = CLIENT.post(login_url, form_data, cookies=response.cookies)
     SESSION_COOKIES = response.cookies
-    if len(SESSION_COOKIES) == 0:
+    if not SESSION_COOKIES:
         return get_session_cookies()
     return SESSION_COOKIES

senpwai/scrapers/pahe/__init__.py

@@ -1,2 +1,2 @@
-from .main import * # noqa: F403
-from .constants import PAHE # noqa: F401
+from .main import *  # noqa: F403
+from .constants import PAHE  # noqa: F401

senpwai/scrapers/pahe/constants.py

@@ -1,4 +1,5 @@
 import re
+
 PAHE = "pahe"
 PAHE_DOMAIN = "animepahe.ru"
 PAHE_HOME_URL = f"https://{PAHE_DOMAIN}"
@@ -22,9 +23,11 @@
 Generates the load episodes link from the provided anime page link and page number.
 Example: {anime_page_link}&page={page_number}
 """
-KWIK_DOMAIN = "kwik.si"
-KWIK_PAGE_REGEX = re.compile(rf"https?://{KWIK_DOMAIN}/f/([^\"']+)")
+KWIK_PAGE_REGEX = re.compile(r"https?://kwik.si/f/([^\"']+)")
 DUB_PATTERN = "eng"
+
 EPISODE_SIZE_REGEX = re.compile(r"\b(\d+)MB\b")
 PARAM_REGEX = re.compile(r"""\(\"(\w+)\",\d+,\"(\w+)\",(\d+),(\d+),(\d+)\)""")
-
+CHAR_MAP = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ+/"
+CHAR_MAP_BASE = 10
+CHAR_MAP_DIGITS = CHAR_MAP[:CHAR_MAP_BASE]

senpwai/scrapers/pahe/main.py

@@ -13,6 +13,8 @@
     match_quality,
 )
 from .constants import (
+    CHAR_MAP_BASE,
+    CHAR_MAP_DIGITS,
     PAHE_HOME_URL,
     FULL_SITE_NAME,
     API_ENTRY_POINT,
@@ -36,6 +38,7 @@
 }
 """
 
+
 def site_request(url: str) -> Response:
     """
     For requests that go specifically to the domain animepahe.ru instead of e.g., pahe.win or kwik.si
@@ -252,32 +255,30 @@ def calculate_total_download_size(bound_info: list[str]) -> int:
     return total_size
 
 
-def get_string(content: str, s1: int) -> int:
-    map_thing = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ+/"
-    s2 = 10
-    map_string = map_thing[:s2]
-    acc = 0
+def get_char_code(content: str, s1: int) -> int:
+    j = 0
     for index, c in enumerate(reversed(content)):
-        acc += (int(c) if c.isdigit() else 0) * int(math.pow(s1, index))
+        j += (int(c) if c.isdigit() else 0) * int(math.pow(s1, index))
     k = ""
-    while acc > 0:
-        k = map_string[acc % s2] + k
-        acc = (acc - (acc % s2)) // s2
-    return int(k) if k.isdigit() else 0
+    while j > 0:
+        k = CHAR_MAP_DIGITS[j % CHAR_MAP_BASE] + k
+        j = (j - (j % CHAR_MAP_BASE)) // CHAR_MAP_BASE
+    return int(k) if k else 0
 
 
 # Courtesy of Saikou app https://github.com/saikou-app/saikou
-def decrypt_token_and_post_url_page(full_key: str, key: str, v1: int, v2: int) -> str:
+# RIP Saikou
+def decrypt_post_form(full_key: str, key: str, v1: int, v2: int) -> str:
     r = ""
     i = 0
     while i < len(full_key):
         s = ""
         while full_key[i] != key[v2]:
             s += full_key[i]
             i += 1
-        for j in range(len(key)):
-            s = s.replace(key[j], str(j))
-        r += chr(get_string(s, v2) - v1)
+        for idx, c in enumerate(key):
+            s = s.replace(c, str(idx))
+        r += chr(get_char_code(s, v2) - v1)
         i += 1
     return r
 
@@ -294,29 +295,30 @@ def get_direct_download_links(
         direct_download_links: list[str] = []
         for pahewin_link in pahewin_download_page_links:
             # Extract kwik page links
-            html_page = CLIENT.get(pahewin_link).text
-            download_link = cast(
-                re.Match[str], KWIK_PAGE_REGEX.search(html_page)
+            pahewin_html_page = CLIENT.get(pahewin_link).text
+            kwik_page_link = cast(
+                re.Match[str], KWIK_PAGE_REGEX.search(pahewin_html_page)
             ).group()
 
-            # Extract direct download links from kwik page links
-            response = CLIENT.get(download_link)
-            cookies = response.cookies
+            # Extract direct download links from kwik html page
+            response = CLIENT.get(kwik_page_link)
+            with open("kwik.html", "wb") as f:
+                f.write(response.content)
             match = cast(re.Match, PARAM_REGEX.search(response.text))
             full_key, key, v1, v2 = (
                 match.group(1),
                 match.group(2),
                 match.group(3),
                 match.group(4),
             )
-            decrypted = decrypt_token_and_post_url_page(full_key, key, int(v1), int(v2))
-            soup = BeautifulSoup(decrypted, PARSER)
+            form = decrypt_post_form(full_key, key, int(v1), int(v2))
+            soup = BeautifulSoup(form, PARSER)
             post_url = cast(str, cast(Tag, soup.form)["action"])
             token_value = cast(str, cast(Tag, soup.input)["value"])
             response = CLIENT.post(
                 post_url,
-                headers=CLIENT.append_headers({"Referer": download_link}),
-                cookies=cookies,
+                headers=CLIENT.append_headers({"Referer": kwik_page_link}),
+                cookies=response.cookies,
                 data={"_token": token_value},
                 allow_redirects=False,
             )

senpwai/scrapers/test.py

@@ -41,6 +41,7 @@ class FailedTest(Exception):
     def __init__(self, msg: str):
         super().__init__(msg)
 
+
 def conditional_print(text: str):
     if not SILENT:
         print(text)
@@ -153,9 +154,17 @@ def test_get_episode_page_links(
     run_time = get_run_time_later()
     test_variables = f"Anime ID: {anime_id}"
     anime_id = cast(str, anime_id)
-    start_page_num, end_page_num, _, first_page = pahe.get_episode_pages_info(anime_page_link, start_episode, end_episode)
+    start_page_num, end_page_num, _, first_page = pahe.get_episode_pages_info(
+        anime_page_link, start_episode, end_episode
+    )
     episode_page_links = pahe.GetEpisodePageLinks().get_episode_page_links(
-        start_episode, end_episode, start_page_num, end_page_num, first_page, anime_page_link, anime_id
+        start_episode,
+        end_episode,
+        start_page_num,
+        end_page_num,
+        first_page,
+        anime_page_link,
+        anime_id,
     )
     rt = run_time()
     fail_if_list_is_empty(
@@ -181,9 +190,7 @@ def test_get_download_page_links(
         (
             pahewin_page,
             pahewin_info,
-        ) = pahe.GetPahewinPageLinks().get_pahewin_page_links_and_info(
-            eps_page_links
-        )
+        ) = pahe.GetPahewinPageLinks().get_pahewin_page_links_and_info(eps_page_links)
         download_page_links, download_info = pahe.bind_sub_or_dub_to_link_info(
             sub_or_dub, pahewin_page, pahewin_info
         )
@@ -238,6 +245,7 @@ def fail_if_list_is_empty(
             test_variables,
         )
 
+
 def test_getting_direct_download_links(
     site: str, download_page_links: list[str], quality: str
 ) -> list[str]:
@@ -742,4 +750,3 @@ def print_metadata(metadata: AnimeMetadata):
 if __name__ == "__main__":
     args = ArgParser(sys.argv)
     run_tests(args)
-

senpwai/senpcli/main.py

@@ -21,6 +21,7 @@
 )
 from senpwai.utils.static import (
     IS_PIP_INSTALL,
+    OS,
     open_folder,
     DUB,
     APP_EXE_PATH as SENPWAI_EXE_PATH,
@@ -609,7 +610,7 @@ def handle_update_check_result(
         )
     if SENPWAI_IS_INSTALLED:
         return print("Update available, install it by updating Senpwai")
-    if sys.platform == "win32":
+    if OS.is_windows:
         print("Update available, would you like to download and install it? (y/n)")
         if input("> ").lower() == "y":
             try: