def get_book(self):
book_id = self._get_book_id()
token = self._get_token(book_id)
chapter = 1
string_text = ''
while True:
url = self._format_content_url(book_id, chapter, token)
response = requests.get(url)
try:
json_response = json.loads(response.text)
for block in json_response['blocks']:
if block['type'] == 'text':
string_text += ' '.join(
self._extract_text(block)) + '\n\n'
print(string_text)
elif block['type'] == 'image':
image_url = self._format_image_url(
book_id, chapter, block['src'], token)
imagename = block['src'].replace('images/', '')
string_text += '\n\n'.format(
imagename, image_url)
chapter += 1
except json.decoder.JSONDecodeError:
print('No more content being exposed by Scribd!')
pdf_out = '{}.pdf'.format(book_id)
print('Generating PDF file: {}'.format(pdf_out))
md2pdf(pdf_out, md_content=string_text)
break
def __exit__(self, exc_type, exc_value, traceback):
"""Exit Function to implement with open method to manage report file.
:param exc_type: Indicates class of exception
:param exc_value: Indicates type of exception
:param traceback: Report with all of the information needed to solve the exception
"""
self.report_file.close()
# Opening the file in reading format
with open(self.filepath, "r", encoding="utf-8") as filemd:
file_str = filemd.read()
# Parse incomptibility syntax
mdtopdf = self.parse_pdf(file_str)
# Generate pdf report if generate_pdf is selected
if self.generate_pdf:
directory = path.dirname(path.abspath(self.filepath))
filename, _ = path.splitext(path.basename(self.filepath))
md2pdf(
f"{directory}/{filename}.pdf",
md_content=mdtopdf,
md_file_path=None,
css_file_path="./templates/markdown-pdf.css",
base_url=directory,
)
def _markdown_to_pdf(self):
"""
Converts markdown to PDF.
"""
md2pdf(self.pdf_path,
md_file_path=self.input_content,
base_url=os.getcwd())
def _get_documents(heads, repo, branches):
css_file = _copy_css_to_tmp()
doc_path = os.path.abspath(os.path.join("..", "docs"))
base_path = os.path.abspath(os.path.join(".."))
for branch in branches:
print("Branch:", branch)
local_name = branch.split("origin/")[-1]
if local_name in heads:
repo.git.checkout(local_name)
else:
repo.git.checkout('-t', branch)
repo.remotes.origin.pull("/".join(branch.split("/")[1:]))
language_name = local_name.split("/")[-1].strip()
pdf_path = os.path.abspath(os.path.join(base_path, language_name))
if os.path.exists(pdf_path):
shutil.rmtree(pdf_path)
os.mkdir(pdf_path)
files = os.listdir(doc_path)
files.sort()
print(files)
mdcontent = ""
for file in files:
if ".md" in file:
md_file_path = os.path.join(doc_path, file)
with open(md_file_path, 'r') as f:
mdcontent += "\n".join(f.readlines())
mdcontent += "\n"
filename = "{}_a4kWs.pdf".format(language_name)
destination = os.path.join(pdf_path, filename)
md2pdf(destination, md_content=mdcontent, css_file_path=css_file)
print("Created ", destination)
repo.git.checkout('master')
os.remove(css_file)
def convert_md_to_pdf(dirname):
original_dir = os.getcwd()
os.chdir(dirname)
for file in glob.glob('*.md'):
pdf_list = glob.glob('*.pdf')
new_filename = file.replace('.md', '.pdf')
if new_filename not in pdf_list and new_filename.lower().replace(
' ', '-') not in pdf_list:
md2pdf.md2pdf(new_filename, md_file_path=file)
os.chdir(original_dir)
else:
line += ". "
text = text.capitalize()
else:
line += " "
line += text
if len(line) > 0:
script += str(cntr) + ". " + line + ".\n"
with open("scripts/script-" + str(x) + ".txt", "w") as w:
w.write(script)
with open("scripts/script-" + str(x) + ".md", "w") as w:
w.write(script)
md2pdf(
"scripts/script-" + str(x) + ".pdf",
script.replace(
"## Script",
"<div style=\"page-break-after: always\"></div>\n\n## Script"))
scripta.sort()
line: str = ""
script: str = "# Script for low-tone and high-tone standalone words.\n"
script += "\n"
script += "The following text contains a list of words with and without high tones.\n"
script += "\n"
script += "Both the high tones and low tones are level and do not glide.\n"
script += "\n"
script += "The final word vowels, unless otherwise marked, should be the word final nasalized high-fall glide.\n"
script += "\n"
from md2pdf.core import md2pdf
md2pdf(pdf_file_path=".",
md_content="content/info-hairball.md",
md_file_path=".",
css_file_path=".",
base_url="https://deytalytics.github.io/deyblog")
return 'bad name'
# get the title of the page
def getPageTitle(fileName):
return names[pages.index(fileName)]
# sidebar file is requires
sidebar = '_Sidebar.md'
if sidebar in files:
# process sidebar
sidebarText = readFile(sidebar)
pages = getPageOrder(sidebarText)
names = getPageNames(sidebarText)
# combine files and write to both markdown and pdf
combined = '\n\n---\n\n'.join([
'#' + getPageTitle(name) + '\n\n' + readFile(name) for name in pages
if name != 'bad name'
])
writeFile('combined.md', combined)
print('Combined markdown finished!')
md2pdf('combined.pdf',
md_content=combined,
css_file_path='styles.css',
base_url=path)
print('PDF finished!')
else:
print('Failed to find _Sidebar.md')
def md_to_pdf(self, pdf_file, body, css_file_path):
md2pdf(pdf_file,
md_content=body,
md_file_path=None,
css_file_path=css_file_path,
base_url=None)