def test_html_to_tables(self):
for file in os.listdir(self.static_path):
if file.endswith('.html'):
html_path = os.path.join(self.static_path, file)
rst = dashtable.html2rst(html_path)
md = dashtable.html2md(html_path)
rst_name = os.path.splitext(file)[0] + '.rst'
rst_path = os.path.join(self.static_path, rst_name)
rst_file = open(rst_path, 'r', encoding='utf-8')
rst_text = rst_file.read().rstrip()
rst_file.close()
try:
self.assertEqual(rst, rst_text)
except AssertionError:
print('MATCH ERROR: ' + ntpath.basename(html_path))
md_name = os.path.splitext(file)[0] + '.md'
md_path = os.path.join(self.static_path, md_name)
md_file = open(md_path, 'r', encoding='utf-8')
md_text = md_file.read().rstrip()
md_file.close()
try:
self.assertEqual(md, md_text)
except AssertionError:
print('MATCH ERROR: ' + ntpath.basename(html_path))
def build_md(doc=None):
from com.sun.star.beans import PropertyValue
if not doc:
document = XSCRIPTCONTEXT.getDocument()
else:
document = doc
html_url = os.path.join(os.path.expanduser('~'), 'temp.html')
html_url = html_url.replace('\\', '/')
if not html_url.startswith('/'):
save_url = 'file:///' + html_url
else:
save_url = 'file://' + html_url
props = [PropertyValue(Name='FilterName', Value='HTML (StarCalc)')]
document.storeToURL(save_url, props)
md = html2md(html_url)
md_url = os.path.join(os.path.expanduser('~'), '.ascii_table.txt')
md_url = md_url.replace('\\', '/')
f = open(md_url, 'w')
f.write(md)
f.close()
os.remove(html_url)
if sys.platform == "win32":
subprocess.call(['start',"", md_url], shell=True)
else:
subprocess.call(['xdg-open', md_url])
from dashtable import html2rst, html2md
import subprocess
import os
for file in os.listdir(os.getcwd() + '/test_files'):
if file.endswith('.html'):
path = os.path.join(os.getcwd(), 'test_files', file)
f = open(path, 'r')
lines = f.readlines()
f.close()
string = ''.join(lines)
converted_rst = html2rst(string)
converted_md = html2md(string)
md_name = os.path.splitext(path)[0] + '.md'
md_file = open(md_name, 'r')
md_lines = md_file.readlines()
md_file.close()
md_string = ''.join(md_lines).rstrip()
if not md_string == converted_md:
print('MarkDown Error: ' + file)
rst_name = os.path.splitext(path)[0] + '.rst'
rst_file = open(rst_name, 'r')
rst_lines = rst_file.readlines()
rst_file.close()
rst_string = ''.join(rst_lines).rstrip()
if not rst_string == converted_rst:
def fetchMe(url):
if "http" not in url:
print(url)
urlToUse = 'https://developer.prod.oculus.com' + url
r = requests.get(urlToUse)
soup = BeautifulSoup(r.text, 'html5lib')
if ":" not in soup.title.string:
title = soup.title.string
else:
title = '"' + soup.title.string + '"'
#description = soup.description.string
firsth1 = soup.select_one("h1")
if firsth1:
soup.select_one("h1").decompose()
imgs = soup.findAll("img")
imageNumber = 0
for img in imgs:
if 'https://www.facebook.com/tr?i' not in img['src']:
print img['src']
extension = get_ext(img['src'])
newFileStub = '/images/' + slugify(
url.decode('utf-8')) + '-' + str(imageNumber) + extension
newFilename = os.getcwd().replace('\\', '/') + newFileStub
print newFilename
"""
if os.path.isfile(newFilename):
os.remove(newFilename)
urllib.urlretrieve(img['src'], newFilename)
"""
imageNumber = imageNumber + 1
img['src'] = newFileStub
imgMD = md(str(img))
img.name = "p"
img.string = imgMD
uls = soup.findAll("ul")
for ul in uls:
ul.string = md(str(ul))
ul.name = 'p'
ols = soup.findAll("ol")
for ol in ols:
ol.string = md(str(ol))
ol.name = 'p'
brs = soup.findAll("br")
for br in brs:
br.replaceWith('\n')
preS = soup.findAll("pre")
for pre in preS:
code = soup.new_tag('code')
tmp = pre.string
pre.string = ''
code.string = tmp
pre.append(code)
samps = soup.findAll("samp")
for samp in samps:
samp.name = "code"
tables = soup.findAll("table")
for table in tables:
print(table)
tableMD = dashtable.html2md(
unicode(table).encode('ascii', 'ignore'))
print(tableMD)
table.string = tableMD
table.name = "p"
links = soup.findAll("a")
for link in links:
link['href'] = link['href'].replace('https://developer.oculus.com',
'')
bodyHTML = str(soup.find(class_='documentation-content'))
output = '---\n'
output += 'title: ' + title + '\n'
#output += 'description: ' + description + '\n'
output += '---\n'
#bodyMD = md(bodyHTML, heading_style='ATX')
bodyMD = str(tomd.convert(str(bodyHTML)))
#bodyMD = pypandoc.convert_text(bodyHTML, 'gfm', format='html')
#print(bodyMD)
output += bodyMD.decode('utf-8')
if url[-1:] == '/':
linkToUse = url[:-1]
else:
linkToUse = url
outputFileName = os.getcwd().replace('\\', '/') + linkToUse + '.md'
#print(outputFileName)
# if file exists, delete it. otherwise, forge the path and write
if os.path.isfile(outputFileName):
os.remove(outputFileName)
else:
dirname = os.path.dirname(outputFileName)
if not os.path.exists(dirname):
os.makedirs(dirname)
f = open(outputFileName, 'w')
f.write(output.encode('utf-8'))
f.close
print(output.encode('utf-8'))
from dashtable import html2rst, html2md
import subprocess
import os
for file in os.listdir(os.getcwd() + '/test_files'):
if file.endswith('.html'):
path = os.getcwd() + '/test_files/' + file
f = open(path, 'r')
lines = f.readlines()
f.close()
string = ''.join(lines)
print(file)
print(html2rst(string))
print('\n')
print(html2md(string))
print('\n')
script = os.path.join(os.getcwd(), 'dashtable/html2rst.py')
filename = os.path.splitext(file)[0]
outfile = os.path.join(os.getcwd(), 'test_files', filename + '.txt')
subprocess.call(['python', script, path, outfile])
import dashtable
print(
dashtable.html2md("""
<table>
<tr><th>Header 1</th><th>Header 2</th></tr>
<tr><td>Data 1</td><td>Data 2</td></tr>
</table>
"""))