diff options
| -rw-r--r-- | .gitignore | 2 | ||||
| -rw-r--r-- | README.md | 3 | ||||
| -rwxr-xr-x | automedia | bin | 0 -> 112552 bytes | |||
| -rwxr-xr-x | automedia.py | 812 | ||||
| -rwxr-xr-x | domain.py | 17 | ||||
| -rwxr-xr-x | episode.py | 73 | ||||
| -rw-r--r-- | requirements.txt | 5 |
7 files changed, 4 insertions, 908 deletions
@@ -1,3 +1,3 @@ .vscode/ __pycache__ -automedia +.gdb_history @@ -10,11 +10,12 @@ Run automedia without any options to see all options. 1. Periodically check and remove in_progress files and their directories. This can happen if the computer crashes while adding rss. 2. Automatically remove torrents that have finished seeding, to reduce memory usage and startup time of transmission. 3. Cache string lengths (too many strcat). +4. Convert python plugins to C. # Requirements ## System transmission-cli, notify-send (optional) ## Python -feedparser, transmissionrpc, lxml, requests, urllib, pure_protobuf (optional, used with mangaplus.shueisha.co.jp) +lxml, requests, pure_protobuf (optional, used with mangaplus.shueisha.co.jp) # Requirements when using read_manga.py ## System rofi, sxiv diff --git a/automedia b/automedia Binary files differnew file mode 100755 index 0000000..84d41c7 --- /dev/null +++ b/automedia diff --git a/automedia.py b/automedia.py deleted file mode 100755 index c13ef26..0000000 --- a/automedia.py +++ /dev/null @@ -1,812 +0,0 @@ -#!/usr/bin/env python3 - -import feedparser -import subprocess -import os -import sys -import time -import json -import uuid -import errno -import signal -import transmissionrpc -import requests -import urllib.parse - -from domain import url_extract_domain -import episode - -from lxml import etree -from datetime import datetime - -script_dir = os.path.dirname(os.path.realpath(sys.argv[0])) - -config_dir = os.path.expanduser("~/.config/automedia") -rss_config_dir = os.path.join(config_dir, "rss") -html_config_dir = os.path.join(config_dir, "html") -automedia_pid_path = "/tmp/automedia.pid" - -only_show_finished_notification = True - -class TrackedRss: - title = None - link = None - json_data = None - - def __init__(self, title, link, json_data): - self.title = title - self.link = link - self.json_data = json_data - -class TrackedHtml: - title = None - link = None - plugin = None - json_data = None - - def __init__(self, title, link, plugin, json_data): - self.title = title - self.link = link - self.plugin = plugin - self.json_data = json_data - -class TorrentProgress: - id = None - name = None - progress = None - - def __init__(self, id, name, progress): - self.id = id - self.name = name - self.progress = progress - -class HtmlItemProgress: - name = None - finished = None - - def __init__(self, name, finished): - self.name = name - self.finished = finished - -def get_file_content_or_none(path): - try: - with open(path, "r") as file: - return file.read() - except FileNotFoundError: - return None - -def get_tracked_rss_by_title(tracked_rss, title): - for t in tracked_rss: - if t.title == title: - return t - return None - -def get_tracked_rss(rss_tracked_dir, existing_tracked_rss): - try: - tracked_rss = [] - for title in os.listdir(rss_tracked_dir): - # Check if we already have the data for the title - #if get_tracked_rss_by_title(existing_tracked_rss, title): - # continue - - in_progress = get_file_content_or_none(os.path.join(rss_tracked_dir, title, ".in_progress")) - if in_progress: - print("Skipping in-progress rss %s" % title) - continue - link = get_file_content_or_none(os.path.join(rss_tracked_dir, title, "link")) - json_data = get_file_content_or_none(os.path.join(rss_tracked_dir, title, "data")) - if json_data: - json_data = json.loads(json_data) - else: - updated = str(time.time()) - json_data = { - "link": link, - "updated": updated, - "downloaded": [] - } - if not link or not json_data: - print("Rss corrupt, link or data missing for rss %s" % title) - continue - tracked_rss.append(TrackedRss(title, link, json_data)) - return tracked_rss - except FileNotFoundError: - return [] - -def rss_update_latest(rss_tracked_dir, rss, latest, url, filename): - updated = str(time.time()) - with open(os.path.join(rss_tracked_dir, rss.title, "updated"), "w") as file: - file.write(updated) - - rss.json_data["updated"] = updated - rss.json_data["downloaded"].append({ "title": latest, "filename": filename, "time": updated, "url": url }) - with open(os.path.join(rss_tracked_dir, rss.title, "data"), "w") as file: - json.dump(rss.json_data, file, indent=4) - -def html_update_latest(html_tracked_dir, html, latest, url): - updated = str(time.time()) - with open(os.path.join(html_tracked_dir, html.title, "updated"), "w") as file: - file.write(updated) - - html.json_data["updated"] = updated - html.json_data["downloaded"].append({ "title": latest, "time": updated, "url": url }) - with open(os.path.join(html_tracked_dir, html.title, "data"), "w") as file: - json.dump(html.json_data, file, indent=4) - -def get_tracked_html(html_tracked_dir): - try: - tracked_html = [] - for title in os.listdir(html_tracked_dir): - in_progress = get_file_content_or_none(os.path.join(html_tracked_dir, title, ".in_progress")) - if in_progress: - print("Skipping in-progress html %s" % title) - continue - link = get_file_content_or_none(os.path.join(html_tracked_dir, title, "link")) - if not link: - print("html corrupt, link missing for html %s" % title) - continue - plugin = get_file_content_or_none(os.path.join(html_tracked_dir, title, "plugin")) - json_data = get_file_content_or_none(os.path.join(html_tracked_dir, title, "data")) - if json_data: - json_data = json.loads(json_data) - else: - updated = str(time.time()) - json_data = { - "plugin": plugin, - "link": link, - "updated": updated, - "downloaded": [] - } - if not plugin or not json_data: - print("html corrupt, plugin or data missing for html %s" % title) - continue - tracked_html.append(TrackedHtml(title, link, plugin, json_data)) - return tracked_html - except FileNotFoundError: - return [] - -# @urgency should either be "low", "normal" or "critical" -def show_notification(title, body, urgency="normal"): - subprocess.Popen(["notify-send", "-u", urgency, "--", title, body]) - -def is_torrent_daemon_running(): - process = subprocess.Popen(["transmission-remote", "-si"], stdout=subprocess.PIPE, stderr=subprocess.PIPE) - process.communicate() - return process.returncode == 0 - -def start_torrent_daemon(download_dir): - # TODO: Make seed ratio configurable - process = subprocess.Popen(["transmission-daemon", "--global-seedratio", "2.0", "--download-dir", download_dir]) - process.communicate() - while not is_torrent_daemon_running(): - time.sleep(0.1) - return process.returncode == 0 - -def add_torrent(torrent_link, tc): - try: - return tc.add_torrent(torrent_link) - except transmissionrpc.TransmissionError as e: - show_notification("Download failed", "Failed to download torrent: {}, Error: {}".format(torrent_link, str(e)), urgency="critical") - return None - -def get_torrent_progress(tc): - torrent_progress = [] - for torrent in tc.get_torrents(): - torrent_progress.append(TorrentProgress(torrent.id, torrent.name, torrent.progress)) - return torrent_progress - -def get_finished_torrents(torrents): - filtered_torrents = [] - for torrent in torrents: - if abs(100.0 - torrent.progress) <= 0.001: - filtered_torrents.append(torrent) - return filtered_torrents - -def get_unfinished_torrents(torrents): - filtered_torrents = [] - for torrent in torrents: - if abs(100.0 - torrent.progress) > 0.001: - filtered_torrents.append(torrent) - return filtered_torrents - -def get_matching_torrents_by_name(torrents1, torrents2): - matching_torrents = [] - for torrent1 in torrents1: - for torrent2 in torrents2: - if torrent1.id == torrent2.id: - matching_torrents.append(torrent1.name) - return matching_torrents - -def get_rss_from_episode_info(episode_name_raw, episode_info): - submitter_query_text = '' - if episode_info.group_name: - submitter_query_text = 'Enter the name of the submitter (leave empty to choose "%s", or type "anon" to choose all submitters): ' % episode_info.group_name - else: - submitter_query_text = 'Enter the name of the submitter (type anon to choose all submitters): ' - - selected_submitter = None - while True: - response = input(submitter_query_text) - if response == "anon": - break - elif len(response) > 0 or (len(response) == 0 and episode_info.group_name): - if len(response) == 0: - response = episode_info.group_name - group_name_escaped = urllib.parse.quote(response) - user_page_response = requests.head("https://nyaa.si/user/" + group_name_escaped) - if user_page_response.ok: - selected_submitter = response - break - else: - print('The submitter "%s" doesn\'t exist on nyaa.si, please choose another submitter.' % response) - - generic_name = episode_info.get_generic_name() - while True: - response = input('Are you sure you want to track "%s" by %s after "%s" ? (Y)es/No: ' % (generic_name, '"%s"' % selected_submitter if selected_submitter else "all submitters", episode_name_raw)) - if len(response) > 0 and response[0].lower() == 'n': - return None - elif len(response) == 0 or response[0].lower() == 'y': - break - - nyaa_rss = 'https://nyaa.si/?page=rss&q={}&c=0_0&f=0'.format(urllib.parse.quote(generic_name)) - if selected_submitter: - nyaa_rss += '&u={}'.format(urllib.parse.quote(selected_submitter)) - return nyaa_rss - -def add_rss(name, url, rss_config_dir, start_after): - feed = feedparser.parse(url) - if feed.bozo == 1: - episode_info = episode.episode_extract_info(url) - if not episode_info.group_name or not episode_info.anime_name: - print("Failed to add rss, error: {}".format(str(feed.bozo_exception))) - return False - - start_after = url - url = get_rss_from_episode_info(url, episode_info) - if not url: - return True - - feed = feedparser.parse(url) - if feed.bozo == 1: - print("Failed to add rss, error: {}".format(str(feed.bozo_exception))) - return False - - if not name: - name = feed["channel"]["title"].replace("/", "_").strip() - - if not name or len(name) == 0: - print("Name not provided and name in rss is empty") - return False - - start_after_url = None - found_start_after = False - for item in feed["items"]: - title = item["title"].replace("/", "_").strip() - if start_after and title == start_after: - found_start_after = True - start_after_url = item["link"] - break - - if start_after and not found_start_after: - print("Failed to find %s in rss %s" % (start_after, url)) - return False - - name = name.replace("/", "_") - rss_dir = os.path.join(rss_config_dir, "tracked", name) - os.makedirs(rss_dir) - - # Create an ".in_progress" file to prevent periodic sync from reading rss data - # before we have finished adding all the data. - # Timestamp is added to it to make it possible to automatically cleanup rss that is corrupted - # (for example if the computer crashes before the in_progress file is removed). - in_progress_filepath = os.path.join(rss_dir, ".in_progress") - with open(in_progress_filepath, "w") as file: - file.write(str(time.time())) - - with open(os.path.join(rss_dir, "link"), "w") as file: - file.write(url) - - updated = str(time.time()) - with open(os.path.join(rss_dir, "updated"), "w") as file: - file.write(updated) - - data = { - "link": url, - "updated": updated, - "downloaded": [] - } - if start_after: - data["downloaded"].append({ "title": start_after, "time": updated, "url": start_after_url }) - - with open(os.path.join(rss_dir, "data"), "w") as file: - json.dump(data, file, indent=4) - - os.remove(in_progress_filepath) - return True - -def add_html(name, url, html_config_dir, start_after): - domain = url_extract_domain(url) - if len(domain) == 0: - print("Invalid url: {}".format(url)) - return False - domain_plugin_path = os.path.join(script_dir, "plugins", domain) - domain_plugin_py_path = os.path.join(script_dir, "plugins", domain + ".py") - - plugin_path = None - if os.path.isfile(domain_plugin_path): - plugin_path = domain_plugin_path - elif os.path.isfile(domain_plugin_py_path): - plugin_path = domain_plugin_py_path - else: - print("Plugin doesn't exist: {}".format(domain)) - return False - - if not name or len(name) == 0: - print("Name not provided or empty") - return False - - start_after_url = None - if start_after: - items = plugin_list(plugin_path, url, None) - if items is None: - return False - - found_start_after = False - for item in reversed(items): - title = item["name"].replace("/", "_").strip() - if start_after and title == start_after: - found_start_after = True - start_after_url = item["url"] - break - - if not found_start_after: - print("Failed to find %s in html %s" % (start_after, url)) - return False - - name = name.replace("/", "_") - html_dir = os.path.join(html_config_dir, "tracked", name) - os.makedirs(html_dir) - - # Create an ".in_progress" file to prevent periodic sync from reading rss data - # before we have finished adding all the data. - # Timestamp is added to it to make it possible to automatically cleanup rss that is corrupted - # (for example if the computer crashes before the in_progress file is removed). - in_progress_filepath = os.path.join(html_dir, ".in_progress") - with open(in_progress_filepath, "w") as file: - file.write(str(int(time.time()))) - - with open(os.path.join(html_dir, "link"), "w") as file: - file.write(url) - - with open(os.path.join(html_dir, "plugin"), "w") as file: - file.write(os.path.basename(plugin_path)) - - updated = str(time.time()) - with open(os.path.join(html_dir, "updated"), "w") as file: - file.write(updated) - - data = { - "plugin": os.path.basename(plugin_path), - "link": url, - "updated": updated, - "downloaded": [] - } - if start_after: - data["downloaded"].append({ "title": start_after, "time": updated, "url": start_after_url }) - - with open(os.path.join(html_dir, "data"), "w") as file: - json.dump(data, file, indent=4) - - os.remove(in_progress_filepath) - return True - -def get_downloaded_item_by_title(tracked_rss, title): - for item in tracked_rss.json_data["downloaded"]: - if item.title == title: - return item - return None - -# Return the title of the newest item -def sync_rss(tracked_rss, tc): - rss_tracked_dir = os.path.join(rss_config_dir, "tracked") - feed = feedparser.parse(tracked_rss.link) - if feed.bozo == 1: - print("{}: Failed to sync rss for url {}, error: {}".format(str(datetime.today().isoformat()), tracked_rss.link, str(feed.bozo_exception))) - if not only_show_finished_notification: - show_notification("RSS Sync failed", "Failed to parse rss for url {}, error: {}".format(tracked_rss.link, str(feed.bozo_exception)), urgency="critical") - return None - - seen_titles = set() - seen_urls = set() - for downloaded_item in tracked_rss.json_data["downloaded"]: - seen_titles.add(downloaded_item["title"].lower().replace(" ", "")) - seen_urls.add(downloaded_item.get("url", "")) - - items = [] - for item in feed["items"]: - title = item["title"].replace("/", "_").strip() - link = item["link"] - # TODO: Goto next page in rss if supported, if we cant find our item on the first page - #if not get_downloaded_item_by_title(tracked_rss, title): - if title.lower().replace(" ", "") in seen_titles or link in seen_urls: - break - items.append(item) - - # Add torrents from the oldest to the newest, and stop when failing to add torrent. - # If it fails, there will be an attempt to add them again after next sync cycle. - latest = None - for item in reversed(items): - title = item["title"].replace("/", "_").strip() - link = item["link"] - - torrent = add_torrent(link, tc) - if not torrent: - show_notification("RSS Sync failed", "Failed to add torrent: {}".format(link), urgency="critical") - return latest - - rss_update_latest(rss_tracked_dir, tracked_rss, title, link, torrent.name) - latest = title - - if not only_show_finished_notification: - show_notification("Download started", latest) - return latest - -def plugin_list(plugin_path, url, latest): - if not latest: - latest = [] - - plugin_name = os.path.basename(plugin_path) - process = None - try: - process = subprocess.Popen([plugin_path, "list", url], stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE) - except FileNotFoundError as e: - print("{}: Plugin failed: Failed to launch plugin list for plugin {}, error: {}".format(str(datetime.today().isoformat()), plugin_name, str(e))) - return None - - stdout, stderr = process.communicate(json.dumps(latest).encode()) - if process.returncode != 0: - print("{}: Plugin failed: Failed to launch plugin list for plugin {} and url {}, error: stdout: {}, stderr: {}".format(str(datetime.today().isoformat()), plugin_name, url, stdout.decode('utf-8'), stderr.decode('utf-8'))) - if not only_show_finished_notification: - show_notification("Plugin failed", "Failed to launch plugin list for plugin {} and url {}, error: stdout: {}, stderr: {}".format(plugin_name, url, stdout.decode('utf-8'), stderr.decode('utf-8')), urgency="critical") - return None - - try: - return json.loads(stdout.decode('utf-8')) - except json.decoder.JSONDecodeError as e: - if not only_show_finished_notification: - show_notification("Plugin failed", "Failed to json decode response of plugin {}, error: {}".format(plugin_name, str(e)), urgency="critical") - return None - -# TODO: Make asynchronous? -def plugin_download(plugin_path, url, download_dir): - process = subprocess.Popen([plugin_path, "download", url, download_dir], stdout=subprocess.PIPE, stderr=subprocess.PIPE) - process.communicate() - return process.returncode == 0 - -def resume_tracked_html(plugin_entry, download_dir, tracked_html, session_id): - # TODO: Instead of redownloading, add resuming. This could be done by adding the files that have been downloaded to a file. - # Redownload items we can detect have stopped. This can happen if the computer crashes or loses connection while downloading. - title_dir = os.path.join(download_dir, tracked_html.title) - try: - for item in os.listdir(title_dir): - item_dir = os.path.join(title_dir, item) - if os.path.isfile(os.path.join(item_dir, ".finished")): - continue - - in_progress_path = os.path.join(item_dir, ".in_progress") - url = get_file_content_or_none(in_progress_path) - # Item has finished downloading - if not url: - continue - - invalid_session = False - try: - with open(os.path.join(item_dir, ".session_id"), "r") as file: - item_session_id = file.read() - if item_session_id != session_id: - invalid_session = True - except FileNotFoundError as e: - invalid_session = True - - if invalid_session: - #if not only_show_finished_notification: - show_notification("Resuming", "Resuming download for item {} with plugin {}".format(os.path.join(tracked_html.title, item), tracked_html.plugin)) - with open(os.path.join(item_dir, ".session_id"), "w") as file: - file.write(session_id) - plugin_download(plugin_entry, url, item_dir) - - except FileNotFoundError as e: - pass - -def build_plugin_list_input(tracked_html): - result = [] - for downloaded_item in tracked_html.json_data["downloaded"]: - result.append({ "title": downloaded_item["title"], "url": downloaded_item.get("url", "") }) - return result - -# Return the title of the newest item -def sync_html(tracked_html, download_dir, session_id): - plugin_entry = os.path.join(script_dir, "plugins", tracked_html.plugin) - resume_tracked_html(plugin_entry, download_dir, tracked_html, session_id) - html_tracked_dir = os.path.join(html_config_dir, "tracked") - - # The program takes and index starting from 1, which is the chapter number - - # Program should print the names of each item (chapter for manga) after "latest", sorted by newest to oldest - # along with the urls to them. - # Only get the items before the one called @latest. The printed data should be in this json format: - # [ - # { - # "name": "Example name", - # "url": "https://example.com" - # }, - # { - # "name": "Another item", - # "url": "https://another.url.com" - # } - # ] - # ./program list url latest - # Note: @latest argument here is optional - items = plugin_list(plugin_entry, tracked_html.link, build_plugin_list_input(tracked_html)) - if not items: - return None - - # A file called ".in_progress" should be added to the download directory when the download is in progress. - # The ".in_progress" file should contain the url that was used to download the item. - # A file called ".finished" should be added to the download directory when the download has finished. - # ./program download url download_dir - latest = None - for item in reversed(items): - url = item["url"] - name = item["name"].replace("/", "_").strip() - item_dir = os.path.join(download_dir, tracked_html.title, name) - os.makedirs(item_dir, exist_ok=True) - - with open(os.path.join(item_dir, ".session_id"), "w") as file: - file.write(session_id) - - if not plugin_download(plugin_entry, url, item_dir): - return latest - - html_update_latest(html_tracked_dir, tracked_html, name, url) - - latest = name - show_notification("Download finished", "{}/{}".format(tracked_html.title, name)) - return latest - -def sync(rss_config_dir, html_config_dir, download_dir, sync_rate_sec): - os.makedirs(download_dir, exist_ok=True) - if not is_torrent_daemon_running(): - if not start_torrent_daemon(download_dir): - print("Failed to start torrent daemon") - exit(2) - print("Started torrent daemon with download directory {}".format(download_dir)) - - rss_tracked_dir = os.path.join(rss_config_dir, "tracked") - html_tracked_dir = os.path.join(html_config_dir, "tracked") - # This is also check rate for html items - check_torrent_status_rate_sec = 15 - unfinished_torrents = [] - - # TODO: Remove this and keep a list of "in progress" html items in memory instead. - session_id = uuid.uuid4().hex - - tc = transmissionrpc.Client("127.0.0.1") - - running = True - tracked_rss = [] - while running: - tracked_rss = get_tracked_rss(rss_tracked_dir, tracked_rss) - for rss in tracked_rss: - print("{}: rss: Syncing {}".format(str(datetime.today().isoformat()), rss.title)) - sync_rss(rss, tc) - # Add last synced timestamp. This together with "updated" file is used to remove series - # that haven't updated in a long time (either finished series or axes series) - - # TODO: Fix. This will fail if the path is removed while its running, - # same with other places. - # To fix, add a command to remove tracked items safely - with open(os.path.join(rss_tracked_dir, rss.title, "synced"), "w") as file: - file.write(str(time.time())) - #else: - # print("No 'latest' item found for rss (maybe we already have the latest item?) %s" % rss.title) - #time.sleep(0.5) # Sleep between fetching rss so we don't get banned for spamming - - tracked_html = get_tracked_html(html_tracked_dir) - for html in tracked_html: - print("{}: html({}): Syncing {}".format(str(datetime.today().isoformat()), html.plugin, html.title)) - sync_html(html, download_dir, session_id) - # Add last synced timestamp. This together with "updated" file is used to remove series - # that haven't updated in a long time (either finished series or axes series) - with open(os.path.join(html_tracked_dir, html.title, "synced"), "w") as file: - file.write(str(time.time())) - #else: - # print("No 'latest' item found for html (maybe we already have the latest item?) %s" % html.title) - #time.sleep(0.5) # Sleep between fetching html so we don't get banned for spamming - - # Check torrent status with sleeping until it's time to sync rss - count = 0 - while count < sync_rate_sec/check_torrent_status_rate_sec: - torrents = get_torrent_progress(tc) - finished_torrents = get_finished_torrents(torrents) - newly_finished_torrents = get_matching_torrents_by_name(finished_torrents, unfinished_torrents) - for newly_finished_torrent in newly_finished_torrents: - show_notification("Download finished", newly_finished_torrent) - unfinished_torrents = get_unfinished_torrents(torrents) - - time.sleep(check_torrent_status_rate_sec) - count += 1 - -def usage(): - print("usage: automedia.py COMMAND") - print("") - print("COMMANDS") - print(" add Add media to track") - print(" sync Start syncing tracked media") - print(" downloaded List downloaded media") - exit(1) - -def usage_add(): - print("usage: automedia.py add <type> <url|filename> [--name name] [--start-after start_after]") - print("OPTIONS") - print(" type The type should be either rss or html") - print(" url The url to the rss or html") - print(" filename The filename of an episode of an existing serie to start track. Currently only works with rss on https://nyaa.si") - print(" --name The display name to be used for the media. Optional for rss, in which case the name will be retries from rss TITLE, required for html") - print(" --start-after The sync should start downloading media after this item. This --start-after value should be the title of the episode/chapter (Optional, default is to start from the first item)") - print("EXAMPLES") - print(" automedia.py add rss 'https://nyaa.si/?page=rss&q=Tejina-senpai+1080p&c=0_0&f=0&u=HorribleSubs'") - print(" automedia.py add html 'https://manganelo.com/manga/read_naruto_manga_online_free3' --name Naruto") - print(" automedia.py add rss '[Erai-raws] Saiki Kusuo no Psi Nan - Kanketsu-hen - 01 [1080p][Multiple Subtitle].mkv'") - exit(1) - -def usage_sync(): - print("usage: automedia.py sync <download_dir>") - print("OPTIONS") - print(" download_dir The path where media should be downloaded to") - print("EXAMPLES") - print(" automedia.py sync /home/adam/Downloads/automedia") - exit(1) - -def command_add(args): - if len(args) < 2: - usage_add() - - media_type = args[0] - media_url = args[1] - media_name = None - start_after = None - - option = None - for arg in args[2:]: - if arg in [ "--name", "--start-after"]: - if option: - usage_add() - option = arg - else: - if not option: - usage_add() - - if option == "--name": - media_name = arg - elif option == "--start-after": - start_after = arg - else: - print("Invalid option %s" % option) - usage_add() - option = None - - if start_after: - start_after = start_after.replace("/", "_").strip() - - media_url = media_url.strip() - - if media_type == "rss": - os.makedirs(rss_config_dir, exist_ok=True) - result = add_rss(media_name, media_url, rss_config_dir, start_after) - if not result: - exit(2) - elif media_type == "html": - if not media_name: - print("missing --name for media of type 'html'") - usage_add() - - os.makedirs(html_config_dir, exist_ok=True) - result = add_html(media_name, media_url, html_config_dir, start_after) - if not result: - exit(2) - else: - print("type should be either rss or html") - usage_add() - -def command_sync(args): - if len(args) < 1: - usage_sync() - - download_dir = args[0] - if not download_dir: - usage_sync() - - pid_file = None - while True: - try: - pid_file = os.open(automedia_pid_path, os.O_CREAT | os.O_EXCL | os.O_WRONLY) - break - except OSError as e: - if e.errno != errno.EEXIST: - raise - - running_automedia_pid = get_file_content_or_none(automedia_pid_path) - if running_automedia_pid: - cmdline = get_file_content_or_none("/proc/%s/cmdline" % running_automedia_pid) - if cmdline and "automedia.py" in cmdline and "sync" in cmdline: - print("AutoMedia is already running with sync") - exit(0) - os.remove(automedia_pid_path) - - def signal_handler(signum, frame): - os.unlink(automedia_pid_path) - exit(1) - signal.signal(signal.SIGINT, signal_handler) - - os.write(pid_file, ("%s" % os.getpid()).encode()) - os.close(pid_file) - - os.makedirs(rss_config_dir, exist_ok=True) - os.makedirs(html_config_dir, exist_ok=True) - - sync_rate_sec = 15 * 60 # every 15 min - sync(rss_config_dir, html_config_dir, download_dir, sync_rate_sec) - -def data_file_get_downloaded(data_filepath): - downloaded = [] - try: - with open(data_filepath, "r") as file: - for item in json.loads(file.read())["downloaded"]: - downloaded.append(item) - except OSError: - pass - return downloaded - -def get_downloaded_items(tracked_dir, is_html): - downloaded_items = [] - try: - downloaded_items = [] - for name in os.listdir(tracked_dir): - data_filepath = os.path.join(tracked_dir, name, "data") - downloaded = data_file_get_downloaded(data_filepath) - for item in downloaded: - if item.get("time"): - if is_html: - item["title"] = os.path.join(name, item["title"]) - filename = item.get("filename") - if filename: - item["title"] = filename - downloaded_items.append(item) - except OSError: - pass - return downloaded_items - -def command_downloaded(): - downloaded_items = [] - downloaded_items.extend(get_downloaded_items(os.path.join(rss_config_dir, "tracked"), False)) - downloaded_items.extend(get_downloaded_items(os.path.join(html_config_dir, "tracked"), True)) - downloaded_items = sorted(downloaded_items, key=lambda item: float(item["time"])) - for item in downloaded_items: - print(item["title"]) - -def main(): - if len(sys.argv) < 2: - usage() - - command = sys.argv[1] - if command == "add": - command_add(sys.argv[2:]) - elif command == "sync": - command_sync(sys.argv[2:]) - elif command == "downloaded": - command_downloaded() - else: - usage() - -if __name__ == "__main__": - main() diff --git a/domain.py b/domain.py deleted file mode 100755 index 0ec8ac7..0000000 --- a/domain.py +++ /dev/null @@ -1,17 +0,0 @@ -#!/usr/bin/env python3 - -def url_extract_domain(url): - index = 0 - if url.startswith("http://"): - index += 7 - elif url.startswith("https://"): - index += 8 - - if url.startswith("www.", index): - index += 4 - - end = url.find(".", index) - if end == -1: - return url[index:] - else: - return url[index:end] diff --git a/episode.py b/episode.py deleted file mode 100755 index 6ac8ab1..0000000 --- a/episode.py +++ /dev/null @@ -1,73 +0,0 @@ -#!/usr/bin/env python3 - -class EpisodeInfo: - group_name = None - anime_name = None - episode = None - resolution = None - extension = None - - def get_generic_name(self): - if not self.group_name or not self.anime_name: - return "" - generic_name = "[%s] %s" % (self.group_name, self.anime_name) - if self.resolution: - generic_name += " [%s]" % self.resolution - if self.extension: - generic_name += self.extension - return generic_name - -def episode_extract_info(episode_name): - episode_name = episode_name.strip() - episode_info = EpisodeInfo() - - if len(episode_name) == 0: - return episode_info - - extension_index = episode_name.rfind('.') - if extension_index != -1: - episode_info.extension = episode_name[extension_index:] - episode_name = episode_name[0:extension_index] - - if episode_name[0] != '[': - return episode_info - - group_name_end = episode_name.find(']') - if group_name_end == -1: - return episode_info - - episode_info.group_name = episode_name[1:group_name_end].strip() - - last_dash = episode_name.rfind('-') - if last_dash == -1: - return episode_info - - episode_info.anime_name = episode_name[group_name_end+1:last_dash].strip() - - resolution_index = episode_name.find('[', last_dash + 1) - if resolution_index == -1: - episode_info.episode = episode_name[last_dash+1:].strip() - else: - episode_info.episode = episode_name[last_dash+1:resolution_index].strip() - resolution_end = episode_name.find(']', resolution_index + 1) - if resolution_end != -1: - episode_info.resolution = episode_name[resolution_index+1:resolution_end] - - return episode_info - -if __name__ == "__main__": - episode_info = episode_extract_info("[Erai-raws] Saiki Kusuo no Psi Nan - Kanketsu-hen - 01 [1080p][Multiple Subtitle].mkv") - print("|{}|".format(episode_info.group_name)) - print("|{}|".format(episode_info.anime_name)) - print("|{}|".format(episode_info.episode)) - print("|{}|".format(episode_info.resolution)) - print("|{}|".format(episode_info.extension)) - print("|{}|".format(episode_info.get_generic_name())) - - episode_info = episode_extract_info("nyaa.si") - print("|{}|".format(episode_info.group_name)) - print("|{}|".format(episode_info.anime_name)) - print("|{}|".format(episode_info.episode)) - print("|{}|".format(episode_info.resolution)) - print("|{}|".format(episode_info.extension)) - print("|{}|".format(episode_info.get_generic_name()))
\ No newline at end of file diff --git a/requirements.txt b/requirements.txt index d9dfe42..4e09b9e 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,3 @@ -feedparser -transmissionrpc lxml requests -pure_protobuf -urllib
\ No newline at end of file +pure_protobuf
\ No newline at end of file |