Compare commits

...

4 Commits
v7.9.0 ... main

Author SHA1 Message Date
Yuvi9587
ef9abacc5d Commit 2025-12-28 18:15:30 +05:30
Yuvi9587
6a36179136 Commit 2025-12-28 09:34:49 +05:30
Yuvi9587
fae9a4bbe2 Commit 2025-12-28 09:25:36 +05:30
Yuvi9587
1ad1e53b57 Commit 2025-12-28 09:23:20 +05:30
8 changed files with 420 additions and 97 deletions

View File

@ -4,6 +4,10 @@ from urllib.parse import urlparse
import json
import requests
import cloudscraper
import ssl
from requests.adapters import HTTPAdapter
from urllib3.poolmanager import PoolManager
from ..utils.network_utils import extract_post_info, prepare_cookies_for_request
from ..config.constants import (
STYLE_DATE_POST_TITLE,
@ -11,6 +15,23 @@ from ..config.constants import (
STYLE_POST_TITLE_GLOBAL_NUMBERING
)
class CustomSSLAdapter(HTTPAdapter):
"""
A custom HTTPAdapter that forces check_hostname=False when using SSL.
This prevents the 'Cannot set verify_mode to CERT_NONE' error.
"""
def init_poolmanager(self, connections, maxsize, block=False):
ctx = ssl.create_default_context()
# Crucial: Disable hostname checking FIRST, then set verify mode
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
self.poolmanager = PoolManager(
num_pools=connections,
maxsize=maxsize,
block=block,
ssl_context=ctx
)
def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_event=None, pause_event=None, cookies_dict=None, proxies=None):
"""
@ -87,36 +108,62 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev
def fetch_single_post_data(api_domain, service, user_id, post_id, headers, logger, cookies_dict=None, proxies=None):
"""
Fetches the full data, including the 'content' field, for a single post using cloudscraper.
Includes RETRY logic for 429 Rate Limit errors.
"""
post_api_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}/post/{post_id}"
logger(f" Fetching full content for post ID {post_id}...")
# FIX: Ensure scraper session is closed after use
scraper = None
try:
scraper = cloudscraper.create_scraper()
# Keep the 300s read timeout for both, but increase connect timeout for proxies
request_timeout = (30, 300) if proxies else (15, 300)
# Retry settings
max_retries = 4
response = scraper.get(post_api_url, headers=headers, timeout=request_timeout, cookies=cookies_dict, proxies=proxies, verify=False)
for attempt in range(max_retries + 1):
scraper = None
try:
scraper = cloudscraper.create_scraper()
response.raise_for_status()
# Mount custom SSL adapter
adapter = CustomSSLAdapter()
scraper.mount("https://", adapter)
full_post_data = response.json()
request_timeout = (30, 300) if proxies else (15, 300)
if isinstance(full_post_data, list) and full_post_data:
return full_post_data[0]
if isinstance(full_post_data, dict) and 'post' in full_post_data:
return full_post_data['post']
return full_post_data
response = scraper.get(post_api_url, headers=headers, timeout=request_timeout, cookies=cookies_dict, proxies=proxies, verify=False)
except Exception as e:
logger(f" ❌ Failed to fetch full content for post {post_id}: {e}")
return None
finally:
if scraper:
scraper.close()
if response.status_code == 429:
wait_time = 20 + (attempt * 10) # 20s, 30s, 40s...
logger(f" ⚠️ Rate Limited (429) on post {post_id}. Waiting {wait_time} seconds before retrying...")
time.sleep(wait_time)
continue # Try loop again
response.raise_for_status()
full_post_data = response.json()
if isinstance(full_post_data, list) and full_post_data:
return full_post_data[0]
if isinstance(full_post_data, dict) and 'post' in full_post_data:
return full_post_data['post']
return full_post_data
except Exception as e:
# Catch "Too Many Requests" if it wasn't caught by status_code check above
if "429" in str(e) or "Too Many Requests" in str(e):
if attempt < max_retries:
wait_time = 20 + (attempt * 10)
logger(f" ⚠️ Rate Limit Error caught: {e}. Waiting {wait_time}s...")
time.sleep(wait_time)
continue
# Only log error if this was the last attempt
if attempt == max_retries:
logger(f" ❌ Failed to fetch full content for post {post_id} after {max_retries} retries: {e}")
return None
finally:
if scraper:
scraper.close()
return None
def fetch_post_comments(api_domain, service, user_id, post_id, headers, logger, cancellation_event=None, pause_event=None, cookies_dict=None, proxies=None):
"""Fetches all comments for a specific post."""
@ -218,11 +265,9 @@ def download_from_api(
if target_post_id and (start_page or end_page):
logger("⚠️ Page range (start/end page) is ignored when a specific post URL is provided (searching all pages for the post).")
# --- FIXED LOGIC HERE ---
# Define which styles require fetching ALL posts first (Sequential Mode)
styles_requiring_fetch_all = [STYLE_DATE_BASED, STYLE_POST_TITLE_GLOBAL_NUMBERING]
# Only enable "fetch all and sort" if the current style is explicitly in the list above
is_manga_mode_fetch_all_and_sort_oldest_first = (
manga_mode and
(manga_filename_style_for_sort_check in styles_requiring_fetch_all) and

0
src/core/hentaifox.txt Normal file
View File

View File

@ -0,0 +1,59 @@
import requests
import re
from bs4 import BeautifulSoup
BASE_URL = "https://hentaifox.com"
HEADERS = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
"Referer": "https://hentaifox.com/",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
}
def get_gallery_id(url_or_id):
"""Extracts numbers from URL or returns the ID string."""
match = re.search(r"(\d+)", str(url_or_id))
return match.group(1) if match else None
def get_gallery_metadata(gallery_id):
"""
Fetches the main gallery page to get the Title and Total Pages.
Equivalent to the first part of the 'hentaifox' function in .sh file.
"""
url = f"{BASE_URL}/gallery/{gallery_id}/"
response = requests.get(url, headers=HEADERS)
response.raise_for_status()
html = response.text
title_match = re.search(r'<title>(.*?)</title>', html)
title = title_match.group(1).replace(" - HentaiFox", "").strip() if title_match else f"Gallery {gallery_id}"
pages_match = re.search(r'Pages: (\d+)', html)
if not pages_match:
raise ValueError("Could not find total pages count.")
total_pages = int(pages_match.group(1))
return {
"id": gallery_id,
"title": title,
"total_pages": total_pages
}
def get_image_link_for_page(gallery_id, page_num):
"""
Fetches the specific reader page to find the actual image URL.
Equivalent to the loop in the 'hentaifox' function:
url="https://hentaifox.com/g/${id}/${i}/"
"""
url = f"{BASE_URL}/g/{gallery_id}/{page_num}/"
response = requests.get(url, headers=HEADERS)
# Extract image source (Bash: grep -Eo 'data-src="..."')
# Regex looks for: data-src="https://..."
match = re.search(r'data-src="(https://[^"]+)"', response.text)
if match:
return match.group(1)
return None

View File

@ -62,7 +62,8 @@ def robust_clean_name(name):
"""A more robust function to remove illegal characters for filenames and folders."""
if not name:
return ""
illegal_chars_pattern = r'[\x00-\x1f<>:"/\\|?*\']'
# FIX: Removed \' from the list so apostrophes are kept
illegal_chars_pattern = r'[\x00-\x1f<>:"/\\|?*]'
cleaned_name = re.sub(illegal_chars_pattern, '', name)
cleaned_name = cleaned_name.strip(' .')
@ -685,7 +686,6 @@ class PostProcessorWorker:
response = requests.get(new_url, headers=file_download_headers, timeout=(30, 300), stream=True, cookies=cookies_to_use_for_file, proxies=self.proxies, verify=False)
response.raise_for_status()
# --- REVISED AND MOVED SIZE CHECK LOGIC ---
total_size_bytes = int(response.headers.get('Content-Length', 0))
if self.skip_file_size_mb is not None:
@ -694,8 +694,7 @@ class PostProcessorWorker:
if file_size_mb < self.skip_file_size_mb:
self.logger(f" -> Skip File (Size): '{api_original_filename}' is {file_size_mb:.2f} MB, which is smaller than the {self.skip_file_size_mb} MB limit.")
return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
# If Content-Length is missing, we can't check, so we no longer log a warning here and just proceed.
# --- END OF REVISED LOGIC ---
num_parts_for_file = min(self.multipart_parts_count, MAX_PARTS_FOR_MULTIPART_DOWNLOAD)
@ -1599,12 +1598,11 @@ class PostProcessorWorker:
should_create_post_subfolder = self.use_post_subfolders
if (not self.use_post_subfolders and self.use_subfolders and
if (not self.use_post_subfolders and
self.sfp_threshold is not None and num_potential_files_in_post >= self.sfp_threshold):
self.logger(f" Post has {num_potential_files_in_post} files (≥{self.sfp_threshold}). Activating Subfolder per Post via [sfp] command.")
should_create_post_subfolder = True
base_folder_names_for_post_content = []
determined_post_save_path_for_history = self.override_output_dir if self.override_output_dir else self.download_root
if not self.extract_links_only and self.use_subfolders:
@ -2462,6 +2460,7 @@ class DownloadThread(QThread):
proxies=self.proxies
)
processed_count_for_delay = 0
for posts_batch_data in post_generator:
if self.isInterruptionRequested():
was_process_cancelled = True
@ -2472,7 +2471,11 @@ class DownloadThread(QThread):
was_process_cancelled = True
break
# --- FIX: Ensure 'proxies' is in this dictionary ---
processed_count_for_delay += 1
if processed_count_for_delay > 0 and processed_count_for_delay % 50 == 0:
self.logger(" ⏳ Safety Pause: Waiting 10 seconds to respect server rate limits...")
time.sleep(10)
worker_args = {
'post_data': individual_post_data,
'emitter': worker_signals_obj,

View File

@ -25,6 +25,7 @@ from .saint2_downloader_thread import Saint2DownloadThread
from .simp_city_downloader_thread import SimpCityDownloadThread
from .toonily_downloader_thread import ToonilyDownloadThread
from .deviantart_downloader_thread import DeviantArtDownloadThread
from .hentaifox_downloader_thread import HentaiFoxDownloadThread
def create_downloader_thread(main_app, api_url, service, id1, id2, effective_output_dir_for_run):
"""
@ -185,6 +186,17 @@ def create_downloader_thread(main_app, api_url, service, id1, id2, effective_out
cancellation_event=main_app.cancellation_event,
parent=main_app
)
# Handler for HentaiFox (New)
if 'hentaifox.com' in api_url or service == 'hentaifox':
main_app.log_signal.emit("🦊 HentaiFox URL detected.")
return HentaiFoxDownloadThread(
url_or_id=api_url,
output_dir=effective_output_dir_for_run,
parent=main_app
)
# ----------------------
# --- Fallback ---
# If no specific handler matched based on service name or URL pattern, return None.

View File

@ -0,0 +1,136 @@
import os
import time
import requests
from PyQt5.QtCore import QThread, pyqtSignal
from ...core.hentaifox_client import get_gallery_metadata, get_image_link_for_page, get_gallery_id
from ...utils.file_utils import clean_folder_name
class HentaiFoxDownloadThread(QThread):
progress_signal = pyqtSignal(str) # Log messages
file_progress_signal = pyqtSignal(str, object) # filename, (current_bytes, total_bytes)
# finished_signal: (downloaded_count, skipped_count, was_cancelled, kept_files_list)
finished_signal = pyqtSignal(int, int, bool, list)
def __init__(self, url_or_id, output_dir, parent=None):
super().__init__(parent)
self.gallery_id = get_gallery_id(url_or_id)
self.output_dir = output_dir
self.is_running = True
self.downloaded_count = 0
self.skipped_count = 0
def run(self):
try:
self.progress_signal.emit(f"🔍 [HentaiFox] Fetching metadata for ID: {self.gallery_id}...")
# 1. Get Info
try:
data = get_gallery_metadata(self.gallery_id)
except Exception as e:
self.progress_signal.emit(f"❌ [HentaiFox] Failed to fetch metadata: {e}")
self.finished_signal.emit(0, 0, False, [])
return
title = clean_folder_name(data['title'])
total_pages = data['total_pages']
# 2. Setup Folder
save_folder = os.path.join(self.output_dir, f"[{self.gallery_id}] {title}")
os.makedirs(save_folder, exist_ok=True)
self.progress_signal.emit(f"📂 Saving to: {save_folder}")
self.progress_signal.emit(f"📄 Found {total_pages} pages. Starting download...")
# 3. Iterate and Download
for i in range(1, total_pages + 1):
if not self.is_running:
self.progress_signal.emit("🛑 Download cancelled by user.")
break
# Fetch image link for this specific page
try:
img_url = get_image_link_for_page(self.gallery_id, i)
if img_url:
ext = img_url.split('.')[-1]
filename = f"{i:03d}.{ext}"
filepath = os.path.join(save_folder, filename)
# Check if exists
if os.path.exists(filepath):
self.progress_signal.emit(f"⚠️ [{i}/{total_pages}] Skipped (Exists): {filename}")
self.skipped_count += 1
else:
self.progress_signal.emit(f"⬇️ [{i}/{total_pages}] Downloading: {filename}")
# CALL NEW DOWNLOAD FUNCTION
success = self.download_image_with_progress(img_url, filepath, filename)
if success:
self.progress_signal.emit(f"✅ [{i}/{total_pages}] Finished: {filename}")
self.downloaded_count += 1
else:
self.progress_signal.emit(f"❌ [{i}/{total_pages}] Failed: {filename}")
self.skipped_count += 1
else:
self.progress_signal.emit(f"❌ [{i}/{total_pages}] Error: No image link found.")
self.skipped_count += 1
except Exception as e:
self.progress_signal.emit(f"❌ [{i}/{total_pages}] Exception: {e}")
self.skipped_count += 1
time.sleep(0.5)
# 4. Final Summary
summary = (
f"\n🏁 [HentaiFox] Task Complete!\n"
f" - Total: {total_pages}\n"
f" - Downloaded: {self.downloaded_count}\n"
f" - Skipped: {self.skipped_count}\n"
)
self.progress_signal.emit(summary)
except Exception as e:
self.progress_signal.emit(f"❌ Critical Error: {str(e)}")
self.finished_signal.emit(self.downloaded_count, self.skipped_count, not self.is_running, [])
def download_image_with_progress(self, url, path, filename):
"""Downloads file while emitting byte-level progress signals."""
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
"Referer": "https://hentaifox.com/"
}
try:
# stream=True is required to get size before downloading body
r = requests.get(url, headers=headers, stream=True, timeout=20)
if r.status_code != 200:
return False
# Get Total Size (in bytes)
total_size = int(r.headers.get('content-length', 0))
downloaded_size = 0
chunk_size = 1024 # 1KB chunks
with open(path, 'wb') as f:
for chunk in r.iter_content(chunk_size):
if not self.is_running:
r.close()
return False
if chunk:
f.write(chunk)
downloaded_size += len(chunk)
self.file_progress_signal.emit(filename, (downloaded_size, total_size))
return True
except Exception as e:
print(f"Download Error: {e}")
return False
def stop(self):
self.is_running = False

View File

@ -1,5 +1,7 @@
import os
import re
import sys
try:
from fpdf import FPDF
FPDF_AVAILABLE = True
@ -18,7 +20,9 @@ try:
self.set_font(self.font_family_main, '', 8)
self.cell(0, 10, 'Page ' + str(self.page_no()), 0, 0, 'C')
except ImportError:
except Exception as e:
print(f"\n❌ DEBUG INFO: Import failed. The specific error is: {e}")
print(f"❌ DEBUG INFO: Python running this script is located at: {sys.executable}\n")
FPDF_AVAILABLE = False
FPDF = None
PDF = None
@ -71,11 +75,6 @@ def add_metadata_page(pdf, post, font_family):
if link_url:
# Styling for clickable link: Blue + Underline
pdf.set_text_color(0, 0, 255)
# Check if font supports underline style directly or just use 'U'
# FPDF standard allows 'U' in style string.
# We use 'U' combined with the font family.
# Note: DejaVu implementation in fpdf2 might handle 'U' automatically or ignore it depending on version,
# but setting text color indicates link clearly enough usually.
pdf.set_font(font_family, 'U', 11)
# Pass the URL to the 'link' parameter
@ -127,9 +126,9 @@ def create_individual_pdf(post_data, output_filename, font_path, add_info_page=F
font_family = _setup_pdf_fonts(pdf, font_path, logger)
if add_info_page:
# add_metadata_page adds the page start itself
add_metadata_page(pdf, post_data, font_family)
# REMOVED: pdf.add_page() <-- This ensures content starts right below the line
else:
pdf.add_page()
@ -206,7 +205,6 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, add_i
for i, post in enumerate(posts_data):
if add_info_page:
add_metadata_page(pdf, post, font_family)
# REMOVED: pdf.add_page() <-- This ensures content starts right below the line
else:
pdf.add_page()
@ -244,6 +242,9 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, add_i
pdf.multi_cell(w=0, h=7, txt=post.get('content', 'No Content'))
try:
output_dir = os.path.dirname(output_filename)
if output_dir and not os.path.exists(output_dir):
os.makedirs(output_dir, exist_ok=True)
pdf.output(output_filename)
logger(f"✅ Successfully created single PDF: '{os.path.basename(output_filename)}'")
return True

View File

@ -106,6 +106,7 @@ from .classes.external_link_downloader_thread import ExternalLinkDownloadThread
from .classes.nhentai_downloader_thread import NhentaiDownloadThread
from .classes.downloader_factory import create_downloader_thread
from .classes.kemono_discord_downloader_thread import KemonoDiscordDownloadThread
from .classes.hentaifox_downloader_thread import HentaiFoxDownloadThread
_ff_ver = (datetime.date.today().toordinal() - 735506) // 28
USERAGENT_FIREFOX = (f"Mozilla/5.0 (Windows NT 10.0; Win64; x64; "
@ -309,6 +310,9 @@ class DownloaderApp (QWidget ):
self.downloaded_hash_counts_lock = threading.Lock()
self.session_temp_files = []
self.single_pdf_mode = False
self.temp_pdf_content_list = []
self.last_effective_download_dir = None
self.save_creator_json_enabled_this_session = True
self.date_prefix_format = self.settings.value(DATE_PREFIX_FORMAT_KEY, "YYYY-MM-DD {post}", type=str)
self.is_single_post_session = False
@ -346,7 +350,7 @@ class DownloaderApp (QWidget ):
self.download_location_label_widget = None
self.remove_from_filename_label_widget = None
self.skip_words_label_widget = None
self.setWindowTitle("Kemono Downloader v7.9.0")
self.setWindowTitle("Kemono Downloader v7.9.1")
setup_ui(self)
self._connect_signals()
if hasattr(self, 'character_input'):
@ -3918,7 +3922,11 @@ class DownloaderApp (QWidget ):
'txt_file': 'coomer.txt',
'url_regex': r'https?://(?:www\.)?coomer\.(?:su|party|st)/[^/\s]+/user/[^/\s]+(?:/post/\d+)?/?'
},
'hentaifox.com': {
'name': 'HentaiFox',
'txt_file': 'hentaifox.txt',
'url_regex': r'https?://(?:www\.)?hentaifox\.com/(?:g|gallery)/\d+/?'
},
'allporncomic.com': {
'name': 'AllPornComic',
'txt_file': 'allporncomic.txt',
@ -3999,7 +4007,8 @@ class DownloaderApp (QWidget ):
'toonily.com', 'toonily.me',
'hentai2read.com',
'saint2.su', 'saint2.pk',
'imgur.com', 'bunkr.'
'imgur.com', 'bunkr.',
'hentaifox.com'
]
for url in urls_to_download:
@ -4087,6 +4096,7 @@ class DownloaderApp (QWidget ):
self._clear_stale_temp_files()
self.session_temp_files = []
self.temp_pdf_content_list = []
processed_post_ids_for_restore = []
manga_counters_for_restore = None
@ -4170,6 +4180,7 @@ class DownloaderApp (QWidget ):
return False
effective_output_dir_for_run = os.path.normpath(main_ui_download_dir) if main_ui_download_dir else ""
self.last_effective_download_dir = effective_output_dir_for_run
if not is_restore:
self._create_initial_session_file(api_url, effective_output_dir_for_run, remaining_queue=self.favorite_download_queue)
@ -5600,8 +5611,18 @@ class DownloaderApp (QWidget ):
permanent, history_data,
temp_filepath) = result_tuple
if temp_filepath: self.session_temp_files.append(temp_filepath)
if temp_filepath:
self.session_temp_files.append(temp_filepath)
# If Single PDF mode is enabled, we need to load the data
# from the temp file into memory for the final aggregation.
if self.single_pdf_setting:
try:
with open(temp_filepath, 'r', encoding='utf-8') as f:
post_content_data = json.load(f)
self.temp_pdf_content_list.append(post_content_data)
except Exception as e:
self.log_signal.emit(f"⚠️ Error reading temp file for PDF aggregation: {e}")
with self.downloaded_files_lock:
self.download_counter += downloaded
self.skip_counter += skipped
@ -5627,47 +5648,73 @@ class DownloaderApp (QWidget ):
self.finished_signal.emit(self.download_counter, self.skip_counter, self.cancellation_event.is_set(), self.all_kept_original_filenames)
def _trigger_single_pdf_creation(self):
"""Reads temp files, sorts them by date, then creates the single PDF."""
self.log_signal.emit("="*40)
self.log_signal.emit("Creating single PDF from collected text files...")
posts_content_data = []
for temp_filepath in self.session_temp_files:
try:
with open(temp_filepath, 'r', encoding='utf-8') as f:
data = json.load(f)
posts_content_data.append(data)
except Exception as e:
self.log_signal.emit(f" ⚠️ Could not read temp file '{temp_filepath}': {e}")
if not posts_content_data:
self.log_signal.emit(" No content was collected. Aborting PDF creation.")
"""
Triggers the creation of a single PDF from collected text content in a BACKGROUND THREAD.
"""
if not self.temp_pdf_content_list:
self.log_signal.emit("⚠️ No content collected for Single PDF.")
return
output_dir = self.dir_input.text().strip() or QStandardPaths.writableLocation(QStandardPaths.DownloadLocation)
default_filename = os.path.join(output_dir, "Consolidated_Content.pdf")
filepath, _ = QFileDialog.getSaveFileName(self, "Save Single PDF", default_filename, "PDF Files (*.pdf)")
# 1. Sort the content
self.log_signal.emit(" Sorting collected content for PDF...")
def sort_key(post):
p_date = post.get('published') or "0000-00-00"
a_date = post.get('added') or "0000-00-00"
pid = post.get('id') or "0"
return (p_date, a_date, pid)
if not filepath:
self.log_signal.emit(" Single PDF creation cancelled by user.")
return
sorted_content = sorted(self.temp_pdf_content_list, key=sort_key)
if not filepath.lower().endswith('.pdf'):
filepath += '.pdf'
# 2. Determine Filename
first_post = sorted_content[0]
creator_name = first_post.get('creator_name') or first_post.get('user') or "Unknown_Creator"
clean_creator = clean_folder_name(creator_name)
filename = f"[{clean_creator}] Complete_Collection.pdf"
# --- FIX 3: Corrected Fallback Logic ---
# Use the stored dir, or fall back to the text input in the UI, or finally the app root
base_dir = self.last_effective_download_dir
if not base_dir:
base_dir = self.dir_input.text().strip()
if not base_dir:
base_dir = self.app_base_dir
output_path = os.path.join(base_dir, filename)
# ---------------------------------------
# 3. Get Options
font_path = os.path.join(self.app_base_dir, 'data', 'dejavu-sans', 'DejaVuSans.ttf')
# Get 'Add Info Page' preference
add_info = True
if hasattr(self, 'more_options_dialog') and self.more_options_dialog:
add_info = self.more_options_dialog.get_add_info_state()
elif hasattr(self, 'add_info_in_pdf_setting'):
add_info = self.add_info_in_pdf_setting
self.log_signal.emit(" Sorting collected posts by date (oldest first)...")
sorted_content = sorted(posts_content_data, key=lambda x: x.get('published', 'Z'))
create_single_pdf_from_content(
sorted_content,
filepath,
font_path,
add_info_page=self.add_info_in_pdf_setting, # Pass the flag here
logger=self.log_signal.emit
# 4. START THE THREAD
self.pdf_thread = PdfGenerationThread(
posts_data=sorted_content,
output_filename=output_path,
font_path=font_path,
add_info_page=add_info,
logger_func=self.log_signal.emit
)
self.log_signal.emit("="*40)
self.pdf_thread.finished_signal.connect(self._on_pdf_generation_finished)
self.pdf_thread.start()
def _on_pdf_generation_finished(self, success, message):
"""Callback for when the PDF thread is done."""
if success:
self.log_signal.emit(f"{message}")
QMessageBox.information(self, "PDF Created", message)
else:
self.log_signal.emit(f"❌ PDF Creation Error: {message}")
QMessageBox.warning(self, "PDF Error", f"Could not create PDF: {message}")
# Optional: Clear the temp list now that we are done
self.temp_pdf_content_list = []
def _add_to_history_candidates(self, history_data):
"""Adds processed post data to the history candidates list and updates the creator profile."""
@ -6589,11 +6636,11 @@ class DownloaderApp (QWidget ):
# Look up the name in the cache, falling back to the ID if not found.
creator_name = self.creator_name_cache.get((service, user_id), user_id)
# Add the new 'creator_name' key to the format_values dictionary.
format_values = {
'id': str(job_details.get('original_post_id_for_log', '')),
'user': user_id,
'creator_name': creator_name, # <-- ADDED
'creator_name': creator_name,
'service': str(job_details.get('service', '')),
'title': post_title,
'name': base,
@ -7028,7 +7075,6 @@ class DownloaderApp (QWidget ):
self.log_signal.emit(f" Fetched a total of {len(all_posts_from_api)} posts from the server.")
# CORRECTED LINE: Assign the list directly without re-filtering
self.new_posts_for_update = all_posts_from_api
if not self.new_posts_for_update:
@ -7056,7 +7102,6 @@ class DownloaderApp (QWidget ):
self.log_signal.emit(f" Update session will save to base folder: {base_download_dir_from_ui}")
raw_character_filters_text = self.character_input.text().strip()
# FIX: Parse both filters and commands from the input string
parsed_character_filter_objects, download_commands = self._parse_character_filters(raw_character_filters_text)
try:
@ -7134,11 +7179,7 @@ class DownloaderApp (QWidget ):
'single_pdf_mode': self.single_pdf_setting,
'project_root_dir': self.app_base_dir,
'processed_post_ids': list(self.active_update_profile['processed_post_ids']),
# FIX: Use the parsed commands dictionary to get the sfp_threshold
'sfp_threshold': download_commands.get('sfp_threshold'),
# FIX: Add all the missing keys
'date_prefix_format': self.date_prefix_format,
'domain_override': download_commands.get('domain_override'),
'archive_only_mode': download_commands.get('archive_only', False),
@ -7171,11 +7212,9 @@ class DownloaderApp (QWidget ):
dialog = EmptyPopupDialog(self.user_data_path, self)
if dialog.exec_() == QDialog.Accepted:
# --- START OF MODIFICATION ---
if hasattr(dialog, 'update_profiles_list') and dialog.update_profiles_list:
self.active_update_profiles_list = dialog.update_profiles_list
# --- NEW LOGIC: Check if user wants to load settings into UI ---
load_settings_requested = getattr(dialog, 'load_settings_into_ui_requested', False)
self.override_update_profile_settings = load_settings_requested
@ -7192,7 +7231,7 @@ class DownloaderApp (QWidget ):
self.link_input.setText(f"{len(self.active_update_profiles_list)} profiles loaded for update check...")
self._start_batch_update_check(self.active_update_profiles_list)
# --- END OF MODIFICATION ---
elif hasattr(dialog, 'selected_creators_for_queue') and dialog.selected_creators_for_queue:
self.active_update_profile = None # Ensure single update mode is off
@ -7441,17 +7480,13 @@ class DownloaderApp (QWidget ):
should_create_artist_folder = False
# --- Check for popup selection scope ---
if item_type == 'creator_popup_selection' and item_scope == EmptyPopupDialog.SCOPE_CREATORS:
should_create_artist_folder = True
# --- Check for global "Artist Folders" scope ---
elif item_type != 'creator_popup_selection' and self.favorite_download_scope == FAVORITE_SCOPE_ARTIST_FOLDERS:
should_create_artist_folder = True
# --- NEW: Check for forced folder flag from batch ---
if self.current_processing_favorite_item_info.get('force_artist_folder'):
should_create_artist_folder = True
# ---------------------------------------------------
if should_create_artist_folder and main_download_dir:
folder_name_key = self.current_processing_favorite_item_info.get('name_for_folder', 'Unknown_Folder')
@ -7469,3 +7504,35 @@ class DownloaderApp (QWidget ):
if not success_starting_download:
self.log_signal.emit(f"⚠️ Failed to initiate download for '{item_display_name}'. Skipping and moving to the next item in queue.")
QTimer.singleShot(100, self._process_next_favorite_download)
class PdfGenerationThread(QThread):
finished_signal = pyqtSignal(bool, str) # success, message
def __init__(self, posts_data, output_filename, font_path, add_info_page, logger_func):
super().__init__()
self.posts_data = posts_data
self.output_filename = output_filename
self.font_path = font_path
self.add_info_page = add_info_page
self.logger_func = logger_func
def run(self):
try:
from .dialogs.SinglePDF import create_single_pdf_from_content
self.logger_func("📄 Background Task: Generating Single PDF... (This may take a while)")
success = create_single_pdf_from_content(
self.posts_data,
self.output_filename,
self.font_path,
self.add_info_page,
logger=self.logger_func
)
if success:
self.finished_signal.emit(True, f"PDF Saved: {os.path.basename(self.output_filename)}")
else:
self.finished_signal.emit(False, "PDF generation failed.")
except Exception as e:
self.finished_signal.emit(False, str(e))