def get_pages(self):
pages = []
if self.config.manual_duplex:
front_pages = sorted(file.name for file in Path('scans').glob(
f'{self.config.name}_*_front.{self.config.scan_format}'))
back_pages = sorted((file.name for file in Path('scans').glob(
f'{self.config.name}_*_back.{self.config.scan_format}')),
reverse=True)
if len(front_pages) != len(back_pages):
raise AssertionError(
'Same number of front and back pages needed!')
for i in range(len(front_pages)):
pages.append(Page(front_pages[i], is_backside=False))
pages.append(Page(back_pages[i], is_backside=True))
else:
for file in sorted(
Path('scans').glob(
f'{self.config.name}_*.{self.config.scan_format}')):
is_backside = bool(
re.match(rf'.*_\d{{3}}[02468].{self.config.scan_format}',
file.name))
pages.append(Page(file.name, is_backside=is_backside))
if not pages:
raise FileNotFoundError(
'no scans found! Seems like scanimage produced no output? Check your setup / scanner.'
)
return pages
def get_page(self, url):
chrome = PyChromeDevTools.ChromeInterface(host="localhost", port=9222)
chrome.Page.enable()
chrome.Page.navigate(url=url)
chrome.wait_event("Page.loadEventFired", timeout=60)
id = chrome.DOM.getDocument()['result']['root']['nodeId']
return Page(
url=url,
html=chrome.DOM.getOuterHTML(nodeId=id)['result']['outerHTML'])
def __init__(self, no_of_pages):
self.buffer_pool = []
self.disk_manager = DiskManager(64)
for i in range(no_of_pages):
self.buffer_pool[i] = Page(i,
64) # Setting default page size to 64
self.replacer = LRUReplacer(self)
self.page_map = {}
self.no_of_pages = no_of_pages
import gi
gi.require_version('Gtk', '3.0')
from gi.repository import Gtk
from src.page import Page
from transliterator.gui.controller import on_start_clicked as on_transliterate_clicked
from lexical_analyzer.gui.controller import on_start_clicked as on_lex_analyzer_clicked
from syntax_analyzer.gui.controller import on_start_clicked as on_syn_analyzer_clicked
settings = Gtk.Settings.get_default()
settings.set_property("gtk-theme-name", "Raleigh")
# settings.set_property("gtk-application-prefer-dark-theme", True) # if you want use dark theme, set second arg to True
window = Gtk.Window(title='Теория формальных граматик и автоматов',
resizable=False)
window.connect('delete-event', Gtk.main_quit)
notebook = Gtk.Notebook()
notebook.append_page(Page(on_transliterate_clicked),
Gtk.Label("Транслитератор"))
notebook.append_page(Page(on_lex_analyzer_clicked),
Gtk.Label("Лехический анализатор"))
notebook.append_page(Page(on_syn_analyzer_clicked),
Gtk.Label("Синтаксический анализатор"))
window.add(notebook)
window.show_all()
Gtk.main()
class confluence:
def __init__(self, *, page_id):
cred = utils.get_credentials('confluence')
self.auth = (cred['user'], cred['password'])
self.page_id = page_id
self.base_url = f'https://{cred["domain"]}/wiki/rest/api/content/{page_id}'
self.domain = cred["domain"]
self.title = None
self.page = None
def __str__(self):
return f'title: {self.title} \n' \
f'page_id: {self.page_id}\n' \
f'at {self.base_url} with no of attachments: ' \
f'{len(self.page.attachments)}'
def save(self, *, dest_folder):
self.__set_page_title()
self.page.title = self.format_title(self.title)
self.download_attachments() \
.download_page_content()
self.page.save(dest_folder=dest_folder)
return self
def __set_page_title(self):
self.title = requests.get(self.base_url,
auth=self.auth).json()['title']
self.page = Page(title=self.title)
return self
@staticmethod
def format_title(title, delimiter='_'):
return title.replace(' ', delimiter)
def download_attachments(self):
"""
Download all page attachments (list(namedtuple))
:return: self
"""
Attachment = namedtuple('Attachment', ['title', 'content'],
verbose=False)
attachements = []
download_info = requests.get(f'{self.base_url}/child/attachment',
auth=self.auth).json()['results']
for elem in download_info:
title = elem['title']
download_url = f'https://{self.domain}/wiki{elem["_links"]["download"]}'
download_content = requests.get(download_url,
auth=self.auth,
stream=True).content
attachements.append(
Attachment(title=title, content=download_content))
self.page.set_attachments(attachements)
return self
def download_page_content(self):
"""
Download raw page source.
:return: self
"""
url = f'{self.base_url}/?expand=body.view'
self.page.set_content(content=requests.get(url, auth=self.auth).json()
['body']['view']['value'])
return self
def __set_page_title(self):
self.title = requests.get(self.base_url,
auth=self.auth).json()['title']
self.page = Page(title=self.title)
return self
from src.page import Page
page = Page('sample.png', 250)
page.analyze_notes()
page.analyze_sharp_flat_natural()
page.draw_sharp_flat_natural()
page.draw_notes()
page.save('hhh.png')
def get_page(self, url):
html = requests.get(url).content
return Page(url=url, html=html)
from src.page import Page
import src.cms as cms
#editable contentfiles to cms
cms.editable = {"Name of content": "body.txt"}
cms.enable()
#clear page folder befor rerender
mypage = Page(
opt={
'url': '/asd',
"template": "document.html",
"contentFiles": {
"body": 'body.txt'
},
"cssList": ['myStyle.css', 'myStyle2.css'],
"jsList": ['first.js', 'second.js']
})
from src.page import Page p = Page() print(p.has_capacity()) p.write(255) p.write(1024) p.write(1023) print(p.read(0)) print(p.read(1)) print(p.read(2))
from src.page import Page
from pdf2image import convert_from_path
import os
import tempfile
import img2pdf
filename = 'target.pdf'
images = convert_from_path('./' + filename, dpi=500)
for i in range(0, len(images)):
print('Start working on page ' + str(i + 1))
images[i].save('./output/' + str(i) + '.jpg', 'JPEG')
page = Page('./output/' + str(i) + '.jpg', 350)
# page.analyze_notes()
# page.analyze_sharp_flat_natural()
page.draw_page()
page.draw_lines()
page.draw_bars()
# page.draw_sharp_flat_natural()
# page.draw_notes()
page.save('./output/' + str(i) + '.jpg')
output = open("./output/output.pdf", "wb")
page_names = []
for filename in os.listdir('./output'):
if filename.endswith(".jpg"):
page_names.append('./output/' + filename)