def receive_custom_amount(update, context):
_ = set_lang(update, context)
if _(CUSTOM_MSG) in update.effective_message.reply_to_message.text:
try:
amount = round(float(update.effective_message.text))
if amount <= 0:
raise ValueError
send_payment_invoice(update, context, amount=amount)
except ValueError:
_ = set_lang(update, context)
update.effective_message.reply_text(
_('The amount you sent is invalid, try again. {}').format(
_(CUSTOM_MSG)),
reply_markup=ForceReply())
def send_payment_invoice(
update: Update,
context: CallbackContext,
query: CallbackQuery,
):
if query is None:
message = update.effective_message
label = message.text
else:
message = query.message
label = query.data
_ = set_lang(update, context)
chat_id = message.chat_id
title = _("Support PDF Bot")
description = _("Say thanks to PDF Bot and help keep it running")
price = PAYMENT_DICT[label]
prices = [LabeledPrice(re.sub(r"\s\(.*", "", label), price * 100)]
context.bot.send_invoice(
chat_id,
title,
description,
PAYMENT_PAYLOAD,
STRIPE_TOKEN,
CURRENCY,
prices,
max_tip_amount=1000,
suggested_tip_amounts=[100, 300, 500, 1000],
)
def check_photo(update: Update, context: CallbackContext) -> int:
message = update.effective_message
message.chat.send_action(ChatAction.TYPING)
photo_file = check_photo_file(update, context)
user_id = message.from_user.id
photo_locks[user_id].acquire()
if photo_file is None:
if not context.user_data[PHOTO_IDS]:
result = ask_first_photo(update, context)
else:
result = ask_next_photo(update, context)
else:
_ = set_lang(update, context)
try:
file_name = photo_file.file_name
except AttributeError:
file_name = _("File name unavailable")
context.user_data[PHOTO_IDS].append(photo_file.file_id)
context.user_data[PHOTO_NAMES].append(file_name)
result = ask_next_photo(update, context)
photo_locks[user_id].release()
return result
def process_photo_task(update, context):
"""
Receive the task and perform the task on the photo
Args:
update: the update object
context: the context object
Returns:
The variable indicating the conversation has ended
"""
if not check_user_data(update, context, PHOTO_ID):
return ConversationHandler.END
_ = set_lang(update, context)
user_data = context.user_data
file_id = user_data[PHOTO_ID]
if update.effective_message.text == _(BEAUTIFY):
process_photo(update, context, [file_id], is_beautify=True)
else:
process_photo(update, context, [file_id], is_beautify=False)
if user_data[PHOTO_ID] == file_id:
del user_data[PHOTO_ID]
return ConversationHandler.END
def send_result_photos(update, context, dir_name, task):
_ = set_lang(update, context)
message = update.effective_message
if message.text == _(PHOTOS):
for photo_name in sorted(os.listdir(dir_name)):
photo_path = os.path.join(dir_name, photo_name)
if os.path.getsize(photo_path) <= MAX_FILESIZE_UPLOAD:
try:
message.chat.send_action(ChatAction.UPLOAD_PHOTO)
message.reply_photo(open(photo_path, "rb"))
except BadRequest:
message.chat.send_action(ChatAction.UPLOAD_DOCUMENT)
message.reply_document(open(photo_path, "rb"))
message.reply_text(
_("See above for all your photos"),
reply_markup=get_support_markup(update, context),
)
update_stats(update, task)
else:
# Compress the directory of photos
shutil.make_archive(dir_name, "zip", dir_name)
# Send result file
send_result_file(update, context, f"{dir_name}.zip", task)
def get_pdf_photos(update, context):
if not check_user_data(update, context, PDF_INFO):
return ConversationHandler.END
_ = set_lang(update, context)
update.effective_message.reply_text(
_("Extracting all the photos in your PDF file"),
reply_markup=ReplyKeyboardRemove(),
)
with tempfile.NamedTemporaryFile() as tf:
user_data = context.user_data
file_id, file_name = user_data[PDF_INFO]
pdf_file = context.bot.get_file(file_id)
pdf_file.download(custom_path=tf.name)
with tempfile.TemporaryDirectory() as tmp_dir_name:
dir_name = os.path.join(tmp_dir_name, "Photos_In_PDF")
os.mkdir(dir_name)
if not write_photos_in_pdf(tf.name, dir_name, file_name):
update.effective_message.reply_text(
_("Something went wrong, try again"))
else:
if not os.listdir(dir_name):
update.effective_message.reply_text(
_("I couldn't find any photos in your PDF file"))
else:
send_result_photos(update, context, dir_name, "get_photos")
# Clean up memory
if user_data[PDF_INFO] == file_id:
del user_data[PDF_INFO]
return ConversationHandler.END
def ask_split_range(update, context):
_ = set_lang(update, context)
update.effective_message.reply_text(
_(
"Send me the range of pages that you'll like to keep\n\n"
"<b>General usage</b>\n"
"<code>: all pages</code>\n"
"<code>22 just the 23rd page</code>\n"
"<code>0:3 the first three pages</code>\n"
"<code>:3 the first three pages</code>\n"
"<code>5: from the 6th page onwards</code>\n"
"<code>-1 last page only</code>\n"
"<code>:-1 all pages but the last page</code>\n"
"<code>-2 second last page only</code>\n"
"<code>-2: last two pages</code>\n"
"<code>-3:-1 third and second last pages only</code>\n\n"
"<b>Advanced usage</b>\n"
"<code>::2 pages 0 2 4 ... to the end</code>\n"
"<code>1:10:2 pages 1 3 5 7 9</code>\n"
"<code>::-1 all pages in reversed order</code>\n"
"<code>3:0:-1 pages 3 2 1 but not 0</code>\n"
"<code>2::-1 pages 2 1 0</code>"
),
parse_mode=ParseMode.HTML,
reply_markup=get_back_markup(update, context),
)
return WAIT_SPLIT_RANGE
def url_to_pdf(update: Update, context: CallbackContext):
_ = set_lang(update, context)
message = update.effective_message
url = message.text
user_data = context.user_data
if user_data is not None and URLS in user_data and url in user_data[URLS]:
message.reply_text(
_("You've sent me this web page already and I'm still converting it")
)
else:
message.reply_text(_("Converting your web page into a PDF file"))
if URLS in user_data:
user_data[URLS].add(url)
else:
user_data[URLS] = {url}
with tempfile.TemporaryDirectory() as dir_name:
out_fn = os.path.join(dir_name, f"{urlparse(url).netloc}.pdf")
try:
HTML(url=url).write_pdf(out_fn)
send_result_file(update, context, out_fn, "url")
except URLFetchingError:
message.reply_text(_("Unable to reach your web page"))
user_data[URLS].remove(url)
def add_ocr_to_pdf(update, context):
if not check_user_data(update, context, PDF_INFO):
return ConversationHandler.END
_ = set_lang(update, context)
update.effective_message.reply_text(
_("Adding an OCR text layer to your PDF file"),
reply_markup=ReplyKeyboardRemove(),
)
with tempfile.NamedTemporaryFile() as tf:
user_data = context.user_data
file_id, file_name = user_data[PDF_INFO]
pdf_file = context.bot.get_file(file_id)
pdf_file.download(custom_path=tf.name)
with tempfile.TemporaryDirectory() as dir_name:
out_fn = os.path.join(dir_name,
f"OCR_{os.path.splitext(file_name)[0]}.pdf")
try:
# logging.getLogger("ocrmypdf").setLevel(logging.WARNING)
ocrmypdf.ocr(tf.name, out_fn, deskew=True, progress_bar=False)
send_result_file(update, context, out_fn, "ocr")
except PriorOcrFoundError:
update.effective_message.reply_text(
_("Your PDF file already has a text layer"))
# Clean up memory
if user_data[PDF_INFO] == file_id:
del user_data[PDF_INFO]
return ConversationHandler.END
def check_pdf(update, context, send_msg=True):
"""
Validate the PDF file
Args:
update: the update object
context: the context object
send_msg: the bool indicating to send a message or not
Returns:
The variable indicating the validation result
"""
pdf_status = PDF_OK
message = update.effective_message
pdf_file = message.document
_ = set_lang(update, context)
if not pdf_file.mime_type.endswith("pdf"):
pdf_status = PDF_INVALID_FORMAT
if send_msg:
message.reply_text(
_("The file you sent is not a PDF file, try again"))
elif pdf_file.file_size >= MAX_FILESIZE_DOWNLOAD:
pdf_status = PDF_TOO_LARGE
if send_msg:
message.reply_text(
_("The PDF file you sent is too large for me to download\n\n"
"I've cancelled your action"))
return pdf_status
def send_pdf_text(update, context, pdf_texts, is_file, out_fn):
_ = set_lang(update, context)
message = update.effective_message
if pdf_texts:
if is_file:
with open(out_fn, "w") as f:
f.write("\n".join(pdf_texts))
send_result_file(update, context, out_fn, "get_text")
else:
msg_text = ""
for pdf_text in pdf_texts:
if len(msg_text) + len(pdf_text) + 1 > MAX_MESSAGE_LENGTH:
message.reply_text(msg_text.strip())
msg_text = ""
msg_text += f" {pdf_text}"
if msg_text:
message.reply_text(msg_text.strip())
message.reply_text(
_("*See above for all the text in your PDF file*"),
parse_mode=ParseMode.MARKDOWN,
)
else:
message.reply_text(_("I couldn't find any text in your PDF file"))
def get_pdf_text(update, context, is_file):
if not check_user_data(update, context, PDF_INFO):
return ConversationHandler.END
_ = set_lang(update, context)
update.effective_message.reply_text(
_("Extracting text from your PDF file"), reply_markup=ReplyKeyboardRemove()
)
with tempfile.NamedTemporaryFile() as tf:
user_data = context.user_data
file_id, file_name = user_data[PDF_INFO]
pdf_file = context.bot.get_file(file_id)
pdf_file.download(custom_path=tf.name)
with tempfile.TemporaryDirectory() as dir_name:
tmp_text = tempfile.TemporaryFile()
with open(tf.name, "rb") as f:
extract_text_to_fp(f, tmp_text)
tmp_text.seek(0)
pdf_texts = textwrap.wrap(tmp_text.read().decode("utf-8").strip())
out_fn = os.path.join(dir_name, f"{os.path.splitext(file_name)[0]}.txt")
send_pdf_text(update, context, pdf_texts, is_file, out_fn)
# Clean up memory
if user_data[PDF_INFO] == file_id:
del user_data[PDF_INFO]
return ConversationHandler.END
def check_user_data(
update: Update, context: CallbackContext, key: str, lock: Lock = None
) -> bool:
"""
Check if the specified key exists in user_data
Args:
update: the update object
context: the context object
key: the string of key
Returns:
The boolean indicating if the key exists or not
"""
data_ok = True
if lock is not None:
lock.acquire()
if key not in context.user_data:
data_ok = False
_ = set_lang(update, context)
update.effective_message.reply_text(_("Something went wrong, start over again"))
if lock is not None:
lock.release()
return data_ok
def cancel(update, context):
_ = set_lang(update, context)
update.effective_message.reply_text(
_("Action cancelled"), reply_markup=ReplyKeyboardRemove()
)
return ConversationHandler.END
def check_text(update: Update, context: CallbackContext) -> int:
update.effective_message.chat.send_action(ChatAction.TYPING)
_ = set_lang(update, context)
if update.effective_message.text == _(CANCEL):
return cancel(update, context)
else:
return receive_feedback(update, context)
def check_doc_task(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text == _(CROP):
return ask_crop_type(update, context)
elif text == _(DECRYPT):
return ask_decrypt_pw(update, context)
elif text == _(ENCRYPT):
return ask_encrypt_pw(update, context)
elif text in [_(EXTRACT_PHOTO), _(TO_PHOTO)]:
return ask_photo_results_type(update, context)
elif text == _(PREVIEW):
return get_pdf_preview(update, context)
elif text == _(RENAME):
return ask_pdf_new_name(update, context)
elif text == _(ROTATE):
return ask_rotate_degree(update, context)
elif text in [_(SCALE)]:
return ask_scale_type(update, context)
elif text == _(SPLIT):
return ask_split_range(update, context)
elif text == _(EXTRACT_TEXT):
return ask_text_type(update, context)
elif text == OCR:
return add_ocr_to_pdf(update, context)
elif text == COMPRESS:
return compress_pdf(update, context)
elif text == _(CANCEL):
return cancel_without_async(update, context)
def send_support_options(update: Update,
context: CallbackContext,
query: CallbackQuery = None):
update.effective_message.reply_chat_action(ChatAction.TYPING)
_ = set_lang(update, context, query)
keyboard = [
[
InlineKeyboardButton(_(THANKS), callback_data=THANKS),
InlineKeyboardButton(_(COFFEE), callback_data=COFFEE),
],
[
InlineKeyboardButton(_(BEER), callback_data=BEER),
InlineKeyboardButton(_(MEAL), callback_data=MEAL),
],
[InlineKeyboardButton(_("Developer"), "https://t.me/Amani_m_h_d")],
]
reply_markup = InlineKeyboardMarkup(keyboard)
text = _("Select how you want to support PDF Bot")
if query is None:
user_id = update.effective_message.from_user.id
else:
user_id = query.from_user.id
context.bot.send_message(user_id, text, reply_markup=reply_markup)
def send_payment_invoice(update, context, query=None, amount=None):
if query is None:
message = update.effective_message
label = message.text
else:
message = query.message
label = query.data
_ = set_lang(update, context)
chat_id = message.chat_id
title = _("Support PDF Bot")
description = _("Say thanks to PDF Bot and help keep it running")
if amount is None:
price = PAYMENT_DICT[label]
else:
label = CUSTOM
price = amount
prices = [LabeledPrice(re.sub(r"\s\(.*", "", label), price * 100)]
context.bot.send_invoice(
chat_id,
title,
description,
PAYMENT_PAYLOAD,
STRIPE_TOKEN,
PAYMENT_PARA,
CURRENCY,
prices,
)
def compare_pdf(update, context):
_ = set_lang(update, context)
message = update.effective_message
message.reply_text(_("Comparing your PDF files"),
reply_markup=ReplyKeyboardRemove())
with tempfile.NamedTemporaryFile() as tf1, tempfile.NamedTemporaryFile(
) as tf2:
# Download PDF files
user_data = context.user_data
first_file_id = user_data[COMPARE_ID]
first_file = context.bot.get_file(first_file_id)
first_file.download(custom_path=tf1.name)
second_file = message.document.get_file()
second_file.download(custom_path=tf2.name)
try:
with tempfile.TemporaryDirectory() as dir_name:
out_fn = os.path.join(dir_name, "Differences.png")
pdf_diff.main(files=[tf1.name, tf2.name], out_file=out_fn)
send_result_file(update, context, out_fn, "compare")
except NoDifferenceError:
message.reply_text(
_("There are no differences in text between your PDF files"))
# Clean up memory and files
if user_data[COMPARE_ID] == first_file_id:
del user_data[COMPARE_ID]
return ConversationHandler.END
def send_support_options(update, context, query=None):
_ = set_lang(update, context, query)
keyboard = [
[
InlineKeyboardButton(_(THANKS), callback_data=THANKS),
InlineKeyboardButton(_(COFFEE), callback_data=COFFEE),
],
[
InlineKeyboardButton(_(BEER), callback_data=BEER),
InlineKeyboardButton(_(MEAL), callback_data=MEAL),
],
[InlineKeyboardButton(_(CUSTOM), callback_data=CUSTOM)],
[
InlineKeyboardButton(_("Help translate PDF Bot"),
"https://crwd.in/telegram-pdf-bot")
],
]
reply_markup = InlineKeyboardMarkup(keyboard)
text = _("Select how you want to support PDF Bot")
if query is None:
user_id = update.effective_message.from_user.id
else:
user_id = query.from_user.id
context.bot.send_message(user_id, text, reply_markup=reply_markup)
def ask_scale_value(update, context, ask_percent=True):
_ = set_lang(update, context)
message = update.effective_message
reply_markup = get_back_markup(update, context)
if message.text == _(BY_PERCENT) or ask_percent:
message.reply_text(
_("Send me the scaling factors for the horizontal and vertical axes\n\n"
"2 will double the axis and 0.5 will halve the axis\n\n"
"*Example: 2 0.5* (this will double the horizontal axis and halve the vertical axis)"
),
reply_markup=reply_markup,
parse_mode=ParseMode.MARKDOWN,
)
return WAIT_SCALE_PERCENT
else:
message.reply_text(
_("Send me the width and height\n\n"
"*Example: 150 200* (this will set the width to 150 and height to 200)"
),
reply_markup=reply_markup,
parse_mode=ParseMode.MARKDOWN,
)
return WAIT_SCALE_DIMENSION
def ask_crop_value(update, context):
_ = set_lang(update, context)
message = update.effective_message
reply_markup = ReplyKeyboardMarkup([[_(BACK)]],
one_time_keyboard=True,
resize_keyboard=True)
if message.text == _(BY_PERCENT):
message.reply_text(
_("Send me a number between {} and {}. This is the percentage of margin space to "
"retain between the content in your PDF file and the page").
format(MIN_PERCENT, MAX_PERCENT),
reply_markup=reply_markup,
)
return WAIT_CROP_PERCENT
else:
message.reply_text(
_("Send me a number that you'll like to adjust the margin size. "
"Positive numbers will decrease the margin size and negative numbers will increase it"
),
reply_markup=reply_markup,
)
return WAIT_CROP_OFFSET
def crop_pdf(update, context, percent=None, offset=None):
_ = set_lang(update, context)
update.effective_message.reply_text(_("Cropping your PDF file"),
reply_markup=ReplyKeyboardRemove())
with tempfile.NamedTemporaryFile(suffix=".pdf") as tf:
user_data = context.user_data
file_id, file_name = user_data[PDF_INFO]
pdf_file = context.bot.get_file(file_id)
pdf_file.download(custom_path=tf.name)
with tempfile.TemporaryDirectory() as dir_name:
out_fn = os.path.join(dir_name, f"Cropped_{file_name}")
command = f'pdf-crop-margins -o "{out_fn}" "{tf.name}"'
if percent is not None:
command += f" -p {percent}"
else:
command += f" -a {offset}"
if run_cmd(command):
send_result_file(update, context, out_fn, "crop")
else:
update.effective_message.reply_text(
_("Something went wrong, try again"))
# Clean up memory
if user_data[PDF_INFO] == file_id:
del user_data[PDF_INFO]
return ConversationHandler.END
def precheckout_check(update, context):
_ = set_lang(update, context)
query = update.pre_checkout_query
if query.invoice_payload != PAYMENT_PAYLOAD:
query.answer(ok=False, error_message=_("Something went wrong"))
else:
query.answer(ok=True)
def check_crop_task(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text in [_(BY_PERCENT), _(BY_SIZE)]:
return ask_crop_value(update, context)
elif text == _(BACK):
return ask_doc_task(update, context)
def check_text(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text == _(BACK):
return ask_first_doc(update, context)
elif text == _(CANCEL):
return cancel(update, context)
def check_text(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text == _(BACK):
return ask_src_doc(update, context)
elif text == _(CANCEL):
return cancel_without_async(update, context)
def check_crop_size(update, context):
_ = set_lang(update, context)
message = update.effective_message
if message.text == _(BACK):
return ask_crop_type(update, context)
try:
offset = float(update.effective_message.text)
except ValueError:
_ = set_lang(update, context)
update.effective_message.reply_text(
_("The number is invalid, try again"))
return WAIT_CROP_OFFSET
return crop_pdf(update, context, offset=offset)
def check_to_photos_task(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text in [_(PHOTOS), _(COMPRESSED)]:
return pdf_to_photos(update, context)
elif text == _(BACK):
return ask_doc_task(update, context)
def check_scale_task(update, context):
_ = set_lang(update, context)
text = update.effective_message.text
if text in [_(BY_PERCENT), _(TO_DIMENSIONS)]:
return ask_scale_value(update, context)
elif text == _(BACK):
return ask_doc_task(update, context)