def docx2txt(filename):
newfilename = filename.replace(u'docx', u'txt')
if os.name == 'nt':
print 'nt'
word = wc.Dispatch('Word.Application')
doc = word.Documents.Open(filename)
doc.SaveAs(newfilename, 4)
doc.Close()
word.Quit() #另存为txt文件，编码为gbk
input_file = open(newfilename, 'r')
gbktxt = input_file.read()
utftxt = gbktxt.decode('gbk').encode('utf-8') #读取txt文件，将gbk转换成utf-8
input_file.close()
output_file = open(newfilename, 'w')
output_file.write(utftxt) #保存utf-8文本
output_file.close()
else:
'''
# 从word（docx格式）中提取text，保存为txt
document = Document(filename)
docText = '\n\n'.join([
paragraph.text.encode('utf-8') for paragraph in document.paragraphs
])
print docText
# 保存文件
# document.save('doc/new-SL351C-A11-01.doc')
output_file = open(newfilename, 'w')
output_file.write(docText)
output_file.close()
'''
#使用pandoc进行转换
pypandoc.convert_file(filename,'markdown','docx',outputfile=newfilename)
print newfilename
def convert_index_to_html(directory):
"""
Looks for the index.rst file, and converts it to index.html using pypandoc.
"""
convert_file('{0}/index.rst'.format(directory),
'html',
outputfile='{0}/index.html'.format(directory))
def main():
home_link = "https://raw.githubusercontent.com/mbadry1/DeepLearning.ai-Summary/master/"
marks_down_links = {
"Deeplearning.ai summary Homepage":
home_link + "Readme.md",
"01- Neural Networks and Deep Learning":
home_link + "1-%20Neural%20Networks%20and%20Deep%20Learning/Readme.md",
"02- Improving Deep Neural Networks Hyperparameter tuning, Regularization and Optimization":
home_link + "2-%20Improving%20Deep%20Neural%20Networks/Readme.md",
"03- Structuring Machine Learning Projects":
home_link + "3-%20Structuring%20Machine%20Learning%20Projects/Readme.md",
"04- Convolutional Neural Networks":
home_link + "4-%20Convolutional%20Neural%20Networks/Readme.md",
"05- Sequence Models":
home_link + "5-%20Sequence%20Models/Readme.md",
}
# Extracting pandoc version
print("pandoc_version:", pypandoc.get_pandoc_version())
print("pandoc_path:", pypandoc.get_pandoc_path())
print("\n")
# Starting downloading and converting
for key, value in marks_down_links.items():
print("Converting", key)
pypandoc.convert_file(
value,
'pdf',
extra_args=['--latex-engine=xelatex', '-V', 'geometry:margin=1.5cm'],
outputfile=(key + ".pdf")
)
print("Converting", key, "completed")
def convert_readme():
print("[*] Converting Markdown README to reStructuredText")
import pypandoc
rst = pypandoc.convert_file('README.md', 'rst')
with open('README.rst', 'w+', encoding='utf-8') as f:
f.write(rst)
print("[*] Finished converting to README.rst ({} bytes)".format(len(rst)))
def test_convert_with_custom_writer(self):
lua_file_content = self.create_sample_lua()
with closed_tempfile('.md', text='#title\n') as file_name:
with closed_tempfile('.lua', text=lua_file_content) as lua_file_name:
expected = u'<h1 id="title">title</h1>{0}'.format(os.linesep)
received = pypandoc.convert_file(file_name, lua_file_name)
self.assertEqualExceptForNewlineEnd(expected, received)
def test_basic_conversion_from_file_with_format(self):
with closed_tempfile('.md', text='#some title\n') as file_name:
expected = u'some title{0}=========={0}{0}'.format(os.linesep)
received = pypandoc.convert(file_name, 'rst', format='md')
self.assertEqualExceptForNewlineEnd(expected, received)
received = pypandoc.convert_file(file_name, 'rst', format='md')
self.assertEqualExceptForNewlineEnd(expected, received)
def get_long_description(self, filename='README.md'):
""" I really prefer Markdown to reStructuredText. PyPi does not.
"""
try:
import pypandoc
description = pypandoc.convert_file('README.md', 'rst', 'md')
except (IOError, ImportError):
description = open("README.md").read()
return description
def convert_readme():
try:
import pypandoc
except ImportError:
return read_rst()
rst = pypandoc.convert_file('README.md', 'rst')
with open('README.rst', 'w') as f:
f.write(rst)
return rst
def long_description(filename = "README.md"):
if os.path.isfile(os.path.expandvars(filename)):
try:
import pypandoc
long_description = pypandoc.convert_file(filename, "rst")
except ImportError:
long_description = open(filename).read()
else:
long_description = ""
return long_description
def finalize(args):
distclean()
try:
check_pypirc()
repository = Repository(REPO_ROOT, args.repo)
img_manager = ImageManager(args.release)
pr_data = repository.find_release_pr(args.release)
if not pr_data:
raise ScriptError('No PR found for {}'.format(args.release))
if not check_pr_mergeable(pr_data):
raise ScriptError('Can not finalize release with an unmergeable PR')
if not img_manager.check_images():
raise ScriptError('Missing release image')
br_name = branch_name(args.release)
if not repository.branch_exists(br_name):
raise ScriptError('No local branch exists for this release.')
gh_release = repository.find_release(args.release)
if not gh_release:
raise ScriptError('No Github release draft for this version')
repository.checkout_branch(br_name)
pypandoc.convert_file(
os.path.join(REPO_ROOT, 'README.md'), 'rst', outputfile=os.path.join(REPO_ROOT, 'README.rst')
)
run_setup(os.path.join(REPO_ROOT, 'setup.py'), script_args=['sdist', 'bdist_wheel'])
merge_status = pr_data.merge()
if not merge_status.merged and not args.finalize_resume:
raise ScriptError(
'Unable to merge PR #{}: {}'.format(pr_data.number, merge_status.message)
)
pypi_upload(args)
img_manager.push_images()
repository.publish_release(gh_release)
except ScriptError as e:
print(e)
return 1
return 0
def read_metadata(self, path, format=None):
metadata_yaml = convert_file(path, to='markdown', format=format,
extra_args=['--template', META_TEMPLATE])
raw_metadata = yaml.safe_load(metadata_yaml)
logger.debug(str(raw_metadata))
metadata = {}
for name, value in raw_metadata.items():
name = name.lower()
value = str(value)
metadata[name] = self.process_metadata(name, value)
return metadata
def read_md(path):
long_desc = ""
if os.path.exists(path):
try:
from pypandoc import convert_file
long_desc = convert_file(path, 'rst')
except:
try:
long_desc = open(path, 'r').read()
except:
pass
return long_desc
def doc_convert(project, logger):
import pypandoc
readme_file = project.expand_path("$distutils_readme_file")
logger.debug("Converting %s into RST format for PyPi documentation...", readme_file)
description = pypandoc.convert_file(readme_file, "rst")
if not hasattr(project, "description") or project.description is None or project.get_property(
"distutils_description_overwrite"):
setattr(project, "description", description)
if not hasattr(project, "summary") or project.summary is None or project.get_property(
"distutils_description_overwrite"):
setattr(project, "summary", description.splitlines()[0].strip())
def read_input(infilename):
""" read text from a file
supported formats:
* plain text
* pdf
* all formats from pandoc
"""
if ".pdf" in infilename:
return extract_from_pdf(infilename)
try:
return pypandoc.convert_file(infilename, 'md')
except Exception as e:
# if fileinput format is not available using pypandoc so try to read it as text
with open(infilename, "r") as infile:
return "".join(infile.readlines())
''' Copyright (C) 2017-2019 Bryant Moscon - [email protected] Please see the LICENSE file for the terms and conditions associated with this software. ''' import sys from setuptools import setup from setuptools import find_packages from setuptools.command.test import test as TestCommand ld = None try: import pypandoc ld = pypandoc.convert_file('README.md', 'rst', format='markdown_github') except BaseException: pass class Test(TestCommand): def run_tests(self): import pytest errno = pytest.main([]) sys.exit(errno) setup( name="cryptofeed", version="0.22.2", author="Bryant Moscon",
def convert_markdown_to_rst(file):
return convert_file(file, "rst")
"--message",
help="Your edit summary and commit message, use quotes for strings. If not provided an automatic message is placed with a timestamp.",
)
parser.add_argument(
"-ng", "--nogit", action="store_true", help="Use this flag if youre not pushing to a git repository."
)
parser.add_argument(
"-i", "--index", action="store_true", help="Adds a link to the published page on your wiki index page."
)
parser.add_argument(
"-html", "--make_html", action="store_true", help="Generates a html version of the file in the working directory."
)
args = parser.parse_args()
# publish to mediawiki
input = args.file.name
output = pypandoc.convert_file(input, "mediawiki")
now = datetime.now
site = mwclient.Site("pzwiki.wdka.nl", "/mw-mediadesign/")
site.force_login = True
site.login(wikiusername, wikipassword)
wikipagename = args.wikipage
page = site.pages["User:"******"/" + wikipagename]
timenow = datetime.now()
now = strftime("%Y-%m-%d %H:%M:%S", gmtime())
automatic_edit_summary = "version pushed from crosspublish.py at " + now
if args.message:
page.save(output, args.message)
else:
page.save(output, automatic_edit_summary)
print(
"Converted " + input + " to mediawiki syntax and published on " + "https://pzwiki.wdka.nl/mw-mediadesign/"
def convert_readme():
import pypandoc
rst = pypandoc.convert_file('README.md', 'rst')
with open('README.rst', 'w') as f:
f.write(rst)
return rst
def main(argv):
"""
Reads in the filepath and starts analysis.
"""
if len(argv) > 1:
# Input via arguments
# TODO: Doesn't work yet
filepath = str(argv[1:])
else:
# Input via console
if sys.version_info[0] < 3: # <- python 2
filepath = str(raw_input("Filepath: "))
else:
filepath = str(input("Filepath: "))
# Settings
language = 'de'
# Data paths
attentionfile = 'data/' + language + '/attentionwords.txt'
ngramfile = 'data/' + language + '/ngramlist.txt'
# Test path
# filepath = '../tests/test.docx'
# Load textfile and convert to plain text
text = pypandoc.convert_file(filepath, 'plain')
# Load attentionwords as list
attentionwords = open(attentionfile, encoding='utf-8').read().splitlines()
# Load ngramlist as list
ngramlist = open(ngramfile, encoding='utf-8').read().splitlines()
# Create a textblob to work with
blob = TextBlob(text)
# Contains all the words
wordlist = blob.words
# Unordered set (unique words)
wordset = list(set(wordlist))
# Contains all the sentences
sentences = blob.sentences
# Contains all the ngrams
ngrams = blob.ngrams(n=2)
## Print all the sentences
#for sentence in sentences:
# print(sentence)
# create wordtable
wordtable = []
for word in wordset:
wordtable.append(
[word, str(wordlist.count(word)),
str(blob.find(word))])
# sort by amount
wordtable = sorted(wordtable, key=lambda word: int(word[1]), reverse=True)
# print amount table
print(tabulate(wordtable))
print("\n")
# print attentionswords list and position where found in text
attentiontable = []
for word in attentionwords:
attentiontable.append([word, str(blob.find(word))])
# sort by position
attentiontable = sorted(attentiontable, key=lambda word: int(word[1]))
# print amount table
print(tabulate(attentiontable))
print("\n")
# print the ngrams which are intersting
phrasetable = []
for ngram in ngrams:
if (ngram[0].lower() == ngram[1].lower()) | (ngram[0].lower()
in ngramlist):
phrase = ' '.join(str(word) for word in ngram)
phrasetable.append([phrase, str(blob.find(phrase))])
# sort by position
phrasetable = sorted(phrasetable, key=lambda word: int(word[1]))
# print amount table
print(tabulate(phrasetable))
print("\n")
import os
from setuptools import setup
try:
import pypandoc
README = pypandoc.convert_file('README.md', 'rst')
except ImportError:
with open(os.path.join(os.path.dirname(__file__), 'README.md')) as readme:
README = readme.read()
# allow setup.py to be run from any path
os.chdir(os.path.normpath(os.path.join(os.path.abspath(__file__), os.pardir)))
setup(
name='drf-schema-adapter',
version='0.9.47',
packages=['drf_auto_endpoint', 'export_app', 'export_app.management',
'export_app.management.commands'],
include_package_data=True,
license='MIT License',
description='Making using Django with frontend libraries and frameworks DRYer',
long_description=README,
url='https://github.com/drf-forms/drf-schema-adapter',
author='Emmanuelle Delescolle, Adrien Brunet, Mauro Bianchi, Mattia Larentis, Aaron Elliot Ross',
author_email='*****@*****.**',
classifiers=[
'Environment :: Web Environment',
'Framework :: Django',
'Framework :: Django :: 1.8',
# -*- coding: utf-8 -*-
from setuptools import setup
import pypandoc
version = {}
with open("pygcgen/version.py") as fh:
exec(fh.read(), version)
changelog = pypandoc.convert_file(
r'CHANGELOG.md',
to='rst',
format='markdown_github',
)
long_desc = """
Automaticaly generate a changelog based on GitHub issues and pull requests.
For each tag there will be a section with closed issues and merged
pull requests. Also there can be user defined sections based on labels.
This package started as a conversion from ruby to python of the
`GitHub Changelog Generator
<https://github.com/skywinder/github-changelog-generator>`__
""" + changelog
setup(
name=version['__title__'],
version=version['__version__'],
How to upload new release
1. change version in setup.py
2. setup twine, see:https://blog.amedama.jp/entry/2017/12/31/175036
3. create zip file: python setup.py sdist
4. upload twine upload --repository pypi dist/hogehoeg
"""
import os
from setuptools import setup, find_packages
PROJECT_PATH = os.path.dirname(os.path.abspath(__file__))
# read README
try:
import pypandoc
readme = pypandoc.convert_file(PROJECT_PATH + '/README.md', 'rst')
except(IOError, ImportError):
readme = open(PROJECT_PATH + '/README.md').read()
setup(
name="pyroombaadapter",
version="0.1.1",
url="https://github.com/AtsushiSakai/PyRoombaAdapter",
author="Atsushi Sakai",
author_email="*****@*****.**",
maintainer='Atsushi Sakai',
maintainer_email='*****@*****.**',
description="A Python library for Roomba Open Interface",
long_description=readme,
python_requires='>3.6.0',
license="MIT",
def read_md(filename):
try:
from pypandoc import convert_file
return convert_file(filename, 'rst')
except (ImportError, OSError):
return open(filename).read()
import ast
import os
import re
from setuptools import setup
import sys
assert sys.version_info >= (3, 5, 0), "flake8-mypy requires Python 3.5+"
current_dir = os.path.abspath(os.path.dirname(__file__))
readme_md = os.path.join(current_dir, 'README.md')
try:
import pypandoc
long_description = pypandoc.convert_file(readme_md, 'rst')
except(IOError, ImportError):
print()
print(
'\x1b[31m\x1b[1mwarning:\x1b[0m\x1b[31m pandoc not found, '
'long description will be ugly (PyPI does not support .md).'
'\x1b[0m'
)
print()
with open(readme_md, encoding='utf8') as ld_file:
long_description = ld_file.read()
_version_re = re.compile(r'__version__\s+=\s+(?P<version>.*)')
import pypandoc
output = pypandoc.convert_file('file.html', 'docx',outputfile="file1.docx")
assert output == ""
import os
import sys
from setuptools import setup, find_packages
try:
this_file = __file__
except NameError:
this_file = sys.argv[0]
os.chdir(os.path.dirname(os.path.abspath(this_file)))
try:
import pypandoc
try:
pypandoc.convert_file("README.md", "rst", outputfile="README.rst")
except (IOError, ImportError, RuntimeError):
pass
long_description = pypandoc.convert_file("README.md", "rst")
except (IOError, ImportError, RuntimeError):
long_description = ""
setup(
name="UCCA",
version="1.0.65",
install_requires=["numpy", "spacy==2.0.11", "requests", "tqdm"],
extras_require={
"visualize": ["matplotlib", "networkx"],
"distances": ["distances", "zss", "munkres"]
},
description="Universal Conceptual Cognitive Annotation",
#!/usr/bin/env python
from setuptools import setup
from gcalcli import __version__
try:
import pypandoc
long_description = pypandoc.convert_file('README.md',
'rst',
format='markdown_github',
extra_args=("--wrap=none", ))
except ImportError:
import sys
print('Warning: No long description generated.', file=sys.stderr)
long_description = ''
author_emails = [
'*****@*****.**', '*****@*****.**', '*****@*****.**'
]
setup(name='gcalcli',
version=__version__,
author='Eric Davis, Brian Hartvigsen, Joshua Crowgey',
author_email=', '.join(author_emails),
maintainer='Joshua Crowgey',
maintainer_email='*****@*****.**',
description='Google Calendar Command Line Interface',
long_description=long_description,
url='https://github.com/insanum/gcalcli',
license='MIT',
packages=['gcalcli'],
data_files=[('share/man/man1', ['docs/man1/gcalcli.1'])],
def read_md(f):
return convert_file(f, 'rst')
def f(filepath):
pypandoc.convert_file(filepath, 'rst')
def convert_readme():
import pypandoc
rst = pypandoc.convert_file('README.md', 'rst')
with open('README.rst', 'w') as f:
f.write(rst)
return rst
warnings.warn("Could not import matlab.engine. " +
"Matlab features will be disabled.")
matlab_installed = False
# Set coverage options in .coveragerc
create_coveragerc.create_coveragerc(matlab_installed=matlab_installed,
lpy_installed=lpy_installed)
# Create .rst README from .md and get long description
if os.path.isfile('README.rst'):
with open('README.rst', 'r') as file:
long_description = file.read()
elif os.path.isfile('README.md'):
try:
import pypandoc
pypandoc.convert_file('README.md', 'rst', outputfile='README.rst')
long_description = pypandoc.convert_file('README.md', 'rst')
except (ImportError, IOError):
with open('README.md', 'r') as file:
long_description = file.read()
else:
raise IOError("Could not find README.rst or README.md")
# Create requirements list based on platform
requirements = [
'numpy>=1.13.0', "scipy", "pyyaml", "pystache", "nose", "pyzmq", "psutil",
"matplotlib<3.0; python_version < '3.5'",
"matplotlib; python_version >= '3.5'", "cerberus", "jsonschema",
'pandas<0.21; python_version == "3.4"', 'pandas; python_version != "3.4"',
"perf", "pint", "unyt", 'sysv_ipc; platform_system != "Windows"'
]
"""
# try:
# import pypandoc
# long_description = pypandoc.convert_file('README.md', 'rst')
# long_description = long_description.replace("\r", "")
# except (ImportError, OSError):
# print("NOTE: pypandoc not available, reading README.md as-is.")
# Edit, switched to using reStructuredText for README file:
try:
long_description = open('README.rst').read()
except FileNotFoundError:
import pypandoc
long_description = pypandoc.convert_file('README.md', to='rst')
# update 'version' and 'download_url', as well as pptx_downsizer.__init__.__version__
setup(
name='ooxml-git-hooks',
description=
'Tools for uncompressing Microsoft Office (Office Open XML) files for better git version control.',
long_description=long_description,
url='https://github.com/scholer/ooxml-git-hooks',
packages=[
'ooxml_git_hooks'
], # List all packages (directories) to include in the source dist.
version='0.1.1-dev', # Update for each new version
# download_url='https://github.com/scholer/ooxml-git-hooks/tarball/0.1.2', # Update for each new version
download_url=
'https://github.com/scholer/ooxml-git-hooks/archive/master.zip',
"""
print("SandboxViolation (disabled): {} {}".format(operation, args))
# pylint: disable=W0212
DirectorySandbox._violation = violation
except ImportError:
pass
disable_sandbox()
try:
# for PyPI, we want a rst readme. For github, we want md. *shruggie*
import pypandoc
long_desc = pypandoc.convert_file('README.md',
'rst',
format=u'markdown_github')
except (IOError, ImportError):
long_desc = open('README.md').read()
ver = open('chiasm_shell/VERSION').read().strip()
setup(
name='chiasm-shell',
description='CLI for assembly/disassembly powered by Keystone/Capstone.',
long_description=long_desc,
version=ver,
url='https://github.com/0xbc/chiasm-shell',
download_url='https://github.com/0xbc/chiasm-shell/tarball/{}'.format(ver),
author='Ben Cheney',
author_email='*****@*****.**',
#!/usr/bin/env python
import pypandoc
import os
for path, dir_list, file_list in os.walk('data/raw/baker'):
for file_name in file_list:
if '.docx' in file_name:
nlist = file_name.split('.')
out_name = nlist[-1]
pypandoc.convert_file(os.path.join(
path, file_name), 'textile', 'docx', outputfile='data/raw/cases/'+out_name+'.txt')
import os
from setuptools import setup
def filepath(fname):
return os.path.join(os.path.dirname(__file__), fname)
exec(compile(open('lifelines/version.py').read(),
'lifelines/version.py', 'exec'))
readme_md = filepath('README.md')
try:
import pypandoc
readme_rst = pypandoc.convert_file(readme_md, 'rst')
except(ImportError):
readme_rst = open(readme_md).read()
setup(
name="lifelines",
version=__version__,
author="Cameron Davidson-Pilon, Jonas Kalderstam",
author_email="*****@*****.**",
description="Survival analysis in Python, including Kaplan Meier, Nelson Aalen and regression",
license="MIT",
keywords="survival analysis statistics data analysis",
url="https://github.com/CamDavidsonPilon/lifelines",
packages=['lifelines',
'lifelines.datasets',
import os
from setuptools import setup, find_packages
def read(fname):
return open(os.path.join(os.path.dirname(__file__), fname)).read()
version = '2.0.0'
try:
import pypandoc
README = pypandoc.convert_file('README.md', 'rst')
CHANGES = pypandoc.convert_file('CHANGES.md', 'rst')
except:
README = read('README.md')
CHANGES = read('CHANGES.md')
setup(
name="pycobertura",
version=version,
author="Alex Conrad",
author_email="*****@*****.**",
maintainer="Alex Conrad",
maintainer_email="*****@*****.**",
description="A Cobertura coverage parser that can diff reports and "
"show coverage progress.",
license="MIT License",
keywords="cobertura coverage diff report parser parse xml",
url="https://github.com/aconrad/pycobertura",
zip_safe=False,
include_package_data=True,
import pypandoc
import panflute
def prepare(doc):
doc.images = []
doc.links = []
def action(elem, doc):
if isinstance(elem, panflute.Image):
doc.images.append(elem)
elif isinstance(elem, panflute.Link):
doc.links.append(elem)
if __name__ == '__main__':
data = pypandoc.convert_file('example.md', 'json')
f = io.StringIO(data)
doc = panflute.load(f)
doc = panflute.run_filter(action, prepare=prepare, doc=doc)
print("\nImages:")
for image in doc.images:
print(image.url)
print("\nLinks:")
for link in doc.links:
print(link.url)
os.environ["CC"] = gcc
os.environ["CXX"] = gcc
else:
global use_openmp
use_openmp = False
logging.warning('No GCC available. Install gcc from Homebrew '
'using brew install gcc.')
set_gcc()
try:
# if we don't have pandoc installed, don't worry about it
import pypandoc
long_description = pypandoc.convert_file("README.md", "rst")
except ImportError:
long_description = ''
setup(
name=NAME,
version=VERSION,
description='Collaborative Filtering for Implicit Datasets',
long_description=long_description,
url='http://github.com/benfred/implicit/',
author='Ben Frederickson',
author_email='*****@*****.**',
license='MIT',
classifiers=[
'Development Status :: 4 - Beta',
def convert_md_to_rtf(mdfile,rtf):
print('Markdown {} to RTF {}'.format(mdfile,rtf))
try:
output = pypandoc.convert_file(mdfile, 'rst', format='md')
elif extension == "java":
md_doc = format_multiple_line_comment(script, "java", "/\*\*", "\*\*/", "//'")
#' Join list of lines
md = '\n'.join(md_doc)
#' Write raw markdown file
md_file = open(filename + ".md", "w")
md_file.write(''.join(md))
md_file.close()
#' # Convert markdown to output format
if args.c and args.o == "html":
pandoc_args=['-c' + args.c, '--toc', '-N', '--self-contained', '--standalone']
output = pypandoc.convert_file(filename + ".md", 'html', outputfile = filename + '.html',
extra_args = pandoc_args)
assert output == ""
else:
output = pypandoc.convert_file(filename + ".md", 'html', outputfile = filename + '.html')
assert output == ""
if args.o != "html":
output = pypandoc.convert_file(filename + ".md", args.o, outputfile = filename + "." +args.o)
assert output == ""
#' Remove markdown output file?
if not args.md:
os.remove(filename + ".md")
from setuptools import setup
from setuptools import find_packages
try:
from pypandoc import convert_file
long_description = convert_file('README.md', 'rst')
except ImportError:
long_description = open('README.md').read()
setup(
name='talkzoho',
version='3.0.3',
description='Asynchronous wrapper for Zoho\'s numerous APIs',
long_description=long_description,
url='https://github.com/A2Z-Cloud/Talk-Zoho',
packages=find_packages(exclude=('tests', 'tests.*')),
author='James Stidard',
author_email='*****@*****.**',
keywords=['talkzoho', 'Zoho', 'async', 'tornado'],
install_requires=[
'fuzzywuzzy',
'python-Levenshtein',
'inflect',
'tornado'])
"""
Format the readme.md file into the sphinx index.rst file.
"""
import re
import pypandoc
from astropy.time import Time
t = Time.now()
t.out_subfmt = 'date'
out = ('.. pyuvdata documentation master file, created by\n'
' make_index.py on {date}\n\n').format(date=t.iso)
readme_text = pypandoc.convert_file('../readme.md', 'rst')
end_text = 'parameters description'
regex = re.compile(end_text.replace(' ', '\s+'))
loc = re.search(regex, readme_text).start()
out += readme_text[0:loc] + end_text + '.'
out += ('\n\nFurther Documentation\n====================================\n'
'.. toctree::\n'
' :maxdepth: 1\n\n'
' tutorial\n'
' parameters\n'
' developer_docs\n')
F = open('index.rst', 'w')
F.write(out)
print("wrote index.rst")
import pypandoc
output = pypandoc.convert_file('./documents/TRSABESP.docx',
'odt',
outputfile="output_converted")
this_file = __file__
except NameError:
this_file = sys.argv[0]
os.chdir(os.path.dirname(os.path.abspath(this_file)))
extras_require = {}
install_requires = []
for requirements_file in glob("requirements.*txt"):
suffix = re.match(r"[^.]*\.(.*)\.?txt", requirements_file).group(1).rstrip(".")
with open(requirements_file) as f:
(extras_require.setdefault(suffix, []) if suffix else install_requires).extend(f.read().splitlines())
try:
import pypandoc
try:
pypandoc.convert_file("README.md", "rst", outputfile="README.rst")
except (IOError, ImportError, RuntimeError):
pass
long_description = pypandoc.convert_file("README.md", "rst")
except (IOError, ImportError, RuntimeError):
long_description = ""
setup(name="UCCA",
version=VERSION,
install_requires=install_requires,
extras_require=extras_require,
description="Universal Conceptual Cognitive Annotation",
long_description=long_description,
author="Daniel Hershcovich",
author_email="*****@*****.**",
from os import path
from setuptools import setup
here = path.abspath(path.dirname(__file__))
# Try to convert markdown readme file to rst format
try:
import pypandoc
md_file = path.join(here, 'README.md')
rst_file = path.join(here, 'README.rst')
pypandoc.convert_file(source_file=md_file, outputfile=rst_file, to='rst')
except (ImportError, OSError, IOError, RuntimeError):
pass
# Get the long description from the relevant file
with open(path.join(here, 'README.rst')) as f:
long_description = f.read()
setup(
name='youtrack-scripts',
version='0.1.23',
python_requires='>=2.6, <3',
packages=[
'youtrackutils', 'youtrackutils.bugzilla', 'youtrackutils.csvClient',
'youtrackutils.fbugz', 'youtrackutils.mantis', 'youtrackutils.redmine',
'youtrackutils.tracLib', 'youtrackutils.utils', 'youtrackutils.zendesk'
],
url='https://github.com/JetBrains/youtrack-python-scripts',
license='Apache 2.0',
maintainer='Alexander Buturlinov',
maintainer_email='*****@*****.**',
text = par.text
if len(text) > 0:
print(text)
file.write(text + "\n")
file.close()
# ===================================================
# PYPANDOC
# ===================================================
import pypandoc
output = pypandoc.convert_file("./data/document-1.docx", "plain", outputfile="output-pypandoc.txt")
assert output == ""
# ===================================================
# GROUPDOCS API
# ===================================================
import groupdocs_conversion_cloud
from shutil import copyfile
client_id = "ENTER CLIENT ID HERE"
client_key = "ENTER CLIENT SECRET HERE"
convert_api = groupdocs_conversion_cloud.ConvertApi.from_keys(client_id, client_key)
def main(**args):
'''
This corresponds to the |rstfromdocx| shell command.
:param args: Keyword arguments. If empty the arguments are taken from ``sys.argv``.
listtable, untable, reflow, reimg default to False.
returns: The file name of the generated file.
'''
import argparse
if not args:
parser = argparse.ArgumentParser(
description=
'''Convert DOCX to RST using Pandoc and additionally copy the images and helper files.'''
)
parser.add_argument('docx', action='store', help='DOCX file')
parser.add_argument('-l',
'--listtable',
action='store_true',
default=False,
help='''postprocess through rstlisttable''')
parser.add_argument('-u',
'--untable',
action='store_true',
default=False,
help='''postprocess through rstuntable''')
parser.add_argument('-r',
'--reflow',
action='store_true',
default=False,
help='''postprocess through rstreflow''')
parser.add_argument('-g',
'--reimg',
action='store_true',
default=False,
help='''postprocess through rstreimg''')
parser.add_argument(
'-j',
'--join',
action='store',
default='012',
help=
'''e.g.002. Join method per column: 0="".join; 1=" ".join; 2="\\n".join'''
)
args = parser.parse_args().__dict__
adocx = args['docx']
extract_media(adocx)
fnrst = _docxrest(adocx)
rst = pypandoc.convert_file(adocx, 'rst', 'docx')
with open(fnrst, 'w', encoding='utf-8', newline='\n') as f:
f.write('.. vim: syntax=rst\n\n')
f.writelines([x + '\n' for x in rst.splitlines()])
_write_confpy(adocx)
_write_index(adocx)
_write_makefile(adocx)
_write_dcx(adocx)
if 'listtable' not in args:
args['listtable'] = False
if 'untable' not in args:
args['untable'] = False
if 'reflow' not in args:
args['reflow'] = False
if 'reimg' not in args:
args['reimg'] = False
if 'join' not in args:
args['join'] = '012'
for a in 'listtable untable reflow reimg'.split():
if args[a]:
args['in_place'] = True
args['sentence'] = True
if a == 'reflow':
args['join'] = '0'
args['rstfile'] = [argparse.FileType('r', encoding='utf-8')(fnrst)]
eval(a)(**args)
return fnrst
def f(filepath):
pypandoc.convert_file(filepath, 'rst')
import os
import sys
import re
from setuptools import setup, find_packages
if sys.argv[-1] == "publish":
os.system("python setup.py sdist upload")
sys.exit()
with open('README.md') as f:
readme = f.read()
# Convert markdown to rst
try:
from pypandoc import convert_file
long_description = convert_file("README.md", "rst")
except:
long_description = ""
version = ''
with io.open('django_react_templatetags/__init__.py', 'r',
encoding='utf8') as fd:
version = re.search(r'^__version__\s*=\s*[\'"]([^\'"]*)[\'"]', fd.read(),
re.MULTILINE).group(1)
setup(
name="django_react_templatetags",
version=version,
description=
("This django library allows you to add React components into your django templates."
), # NOQA
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Dec 1 18:39:12 2016
@author: Pranavtadepalli
"""
import pypandoc
#converts markdown to reStructured
z = pypandoc.convert_file('Users/Pranavtadepalli/WordInfo/README.rst','rst',format='markdown')
#writes converted file
with open('WordInfo/README.rst','w') as outfile:
outfile.write(z)
def read(fname):
rst = pypandoc.convert_file(os.path.join(os.path.dirname(__file__), fname),
'rst',
format='md')
return rst
except ImportError:
print('Wheel library missing. Please run "pip install wheel"')
sys.exit()
os.system('python setup.py sdist upload')
os.system('python setup.py bdist_wheel upload')
sys.exit()
if sys.argv[-1] == 'tag':
print("Tagging the version on github:")
os.system("git tag -a %s -m 'version %s'" % (version, version))
os.system("git push --tags")
sys.exit()
try:
import pypandoc
long_description = pypandoc.convert_file('README.md', 'rst') + \
pypandoc.convert_file('docs/HISTORY.md', 'rst')
except BaseException:
long_description = ''
license = open('LICENSE').read()
setup(
name='callisto-core',
version=version,
description='Report intake, escrow, matching and secure delivery code for Callisto, an online reporting system for sexual assault.',
long_description=long_description,
license=license,
author='Project Callisto',
author_email='*****@*****.**',
url='https://github.com/project-callisto/callisto-core',
from setuptools import setup
long_description = ""
try:
import subprocess
import pypandoc
long_description = pypandoc.convert_file("README.md",
to="rst",
format="md")
except ImportError:
pass
setup(
name="asterisk_dialplan",
version="0.2.0",
author="Andrew Yager",
author_email="*****@*****.**",
license="BSD",
packages=["asterisk_dialplan"],
description=
"Helpers to convert numbers to dialplan strings for use in Asterisk",
long_description=long_description,
classifiers=[
"Development Status :: 4 - Beta",
"Topic :: Communications :: Telephony",
"Topic :: Software Development :: Libraries",
"License :: OSI Approved :: BSD License",
],
#!/usr/bin/env python
import pypandoc
import os
import yara
import fnmatch
from codecs import open
rules_dir = 'apkid/rules/'
compiled_rules_path = "%srules.yarc" % rules_dir
print "[*] Converting Markdown README to reStructuredText ..."
rst = pypandoc.convert_file('README.md', 'rst')
with open('README.rst', 'w+', encoding='utf-8') as f:
f.write(rst)
print "[*] Finished converting to README.rst (%s bytes)" % len(rst)
yara_files = {}
for root, dirnames, filenames in os.walk(rules_dir):
for filename in fnmatch.filter(filenames, '*.yar'):
path = os.path.join(root, filename)
yara_files[path] = path
#print yara_files
rules = yara.compile(filepaths=yara_files)
print "[*] Compiling %d Yara rules ..." % len(yara_files)
rules.save(compiled_rules_path)
print "[*] Saved rules to %s" % compiled_rules_path
#print "[*] Registering ..."
#os.system("python setup.py register")
import pypandoc
output = pypandoc.convert_file('README.md', 'rst', outputfile="README.rst")
assert output == ""
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from setuptools import setup, find_packages
# I really prefer Markdown to reStructuredText. PyPi does not. This allows me
# to have things how I'd like, but not throw complaints when people are trying
# to install the package and they don't have pypandoc or the README in the
# right place.
try:
import pypandoc
long_description = pypandoc.convert_file('README.md', 'rst')
except (IOError, ImportError):
long_description = open('README.md').read()
about = {}
with open('src/clikraken/__about__.py') as f:
exec(f.read(), about)
# now we have a about['__version__'] variable
setup(
name=about['__title__'],
version=about['__version__'],
packages=find_packages('src'),
package_dir={'': 'src'},
author=about['__author__'],
author_email=about['__email__'],
license=about['__license__'],
description=about['__summary__'],
long_description=long_description,
include_package_data=True,
for i in range(len(chapters)):
#getting the chapters using the ID
print("Getting Chapter", i+1, "....")
story = requests.get("https://www.wattpad.com/apiv2/storytext?id=" + str(chapters[i]['ID']), headers={'User-Agent': 'Mozilla/5.0'})
try:
story.raise_for_status()
except Exception as exc:
print("There was a problem: %s" % (exc))
#Creating soup
soup_res = bs4.BeautifulSoup(story.text, 'html.parser')
#Adding Content of chapters to the file
file.write("<br><br><h2>Chapter "+str(i+1)+" : '"+ chapters[i]['TITLE'] +"'</h2><br><br>")
file.write(soup_res.prettify())
file.write("</body></html>")
#closing the file
file.close()
#Output
print("saved "+ story_name+".html")
print("Generating Epub...")
#Using Pypandoc to convert html to epub
output = pypandoc.convert_file(story_name+".html", 'epub3', outputfile=story_name+".epub", extra_args=['--epub-chapter-level=2'])
assert output == ""
print("saved "+ story_name+".epub")
def read_md(f):
rst = convert_file(f, 'rst')
rst = rst.replace('\r', '') # fix #773
return rst
def read_md(f):
return convert_file(f, 'rst', format='md')
