def _url_to_epub(
self):
"""*generate the epub book from a URL*
"""
self.log.info('starting the ``_url_to_epub`` method')
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=self.log,
settings=self.settings,
url=self.urlOrPath,
outputDirectory=self.outputDirectory,
title=self.title, # SET TO FALSE TO USE WEBPAGE TITLE,
style=False, # add simpdf's styling to the HTML document
metadata=True, # include metadata in generated HTML (e.g. title),
h1=False # include title as H1 at the top of the doc
)
html = cleaner.clean()
if not html:
return None
if self.footer:
footer = self._tmp_html_file(self.footer)
footer = '"%(footer)s"' % locals()
else:
footer = ""
if self.header:
header = self._tmp_html_file(self.header)
header = '"%(header)s"' % locals()
else:
header = ""
# HTML SOURCE FILE
epub = html.replace(".html", ".epub")
pandoc = self.settings["executables"]["pandoc"]
cmd = """%(pandoc)s -S -s -f html -t epub3 %(header)s "%(html)s" %(footer)s -o "%(epub)s" """ % locals(
)
p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
stdout, stderr = p.communicate()
self.log.debug('output: %(stdout)s' % locals())
try:
with open(epub):
pass
fileExists = True
except IOError:
fileExists = False
raise IOError(
"the epub %s does not exist on this machine, here is the failure message: %s" % (epub, stderr))
os.remove(html)
self.log.info('completed the ``_url_to_epub`` method')
return epub
def _url_to_epub(self):
"""*generate the epub book from a URL*
"""
self.log.debug('starting the ``_url_to_epub`` method')
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=self.log,
settings=self.settings,
url=self.urlOrPath,
outputDirectory=self.outputDirectory,
title=self.title, # SET TO FALSE TO USE WEBPAGE TITLE,
style=False, # add simpdf's styling to the HTML document
metadata=True, # include metadata in generated HTML (e.g. title),
h1=False # include title as H1 at the top of the doc
)
html = cleaner.clean()
if not html:
return None
if self.footer:
footer = self._tmp_html_file(self.footer)
footer = '"%(footer)s"' % locals()
else:
footer = ""
if self.header:
header = self._tmp_html_file(self.header)
header = '"%(header)s"' % locals()
else:
header = ""
# HTML SOURCE FILE
epub = html.replace(".html", ".epub")
pandoc = self.settings["executables"]["pandoc"]
cmd = """%(pandoc)s -S -s -f html -t epub3 %(header)s '%(html)s' %(footer)s -o '%(epub)s' """ % locals(
)
p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
stdout, stderr = p.communicate()
self.log.debug('output: %(stdout)s' % locals())
try:
with open(epub):
pass
fileExists = True
except IOError:
fileExists = False
raise IOError(
"the epub %s does not exist on this machine, here is the failure message: %s"
% (epub, stderr))
os.remove(html)
self.log.debug('completed the ``_url_to_epub`` method')
return epub
def test_htmlCleaner_function(self):
from polyglot import htmlCleaner
this = htmlCleaner(
log=log,
settings=settings,
url="http://www.thespacedoctor.co.uk/blog/2016/09/26/mysqlSucker-index.html",
outputDirectory=pathToOutputDir,
title=False
)
this.clean()
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=log,
settings=settings,
url="http://www.thespacedoctor.co.uk/blog/2016/09/26/mysqlSucker-index.html",
outputDirectory=pathToOutputDir,
title="my_clean_doc.html"
)
cleaner.clean()
def test_htmlCleaner_function_exception(self):
from polyglot import htmlCleaner
try:
this = htmlCleaner(log=log,
settings=settings,
fakeKey="break the code")
this.get()
assert False
except Exception, e:
assert True
print str(e)
def test_htmlCleaner_function(self):
from polyglot import htmlCleaner
this = htmlCleaner(
log=log,
settings=settings,
url=
"http://www.thespacedoctor.co.uk/blog/2016/09/26/mysqlSucker-index.html",
outputDirectory=pathToOutputDir,
title=False)
this.clean()
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=log,
settings=settings,
url=
"http://www.thespacedoctor.co.uk/blog/2016/09/26/mysqlSucker-index.html",
outputDirectory=pathToOutputDir,
title="my_clean_doc.html")
cleaner.clean()
def test_htmlCleaner_function_exception(self):
from polyglot import htmlCleaner
try:
this = htmlCleaner(
log=log,
settings=settings,
fakeKey="break the code"
)
this.get()
assert False
except Exception, e:
assert True
print str(e)
def _print_original_webpage(
self):
"""*print the original webpage*
**Return:**
- ``pdfPath`` -- the path to the generated PDF
"""
self.log.info('starting the ``_print_original_webpage`` method')
if not self.title:
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=self.log,
settings=self.settings,
url=self.url,
outputDirectory=self.folderpath,
title=self.title, # SET TO FALSE TO USE WEBPAGE TITLE,
style=True, # add polyglot's styling to the HTML document
# include metadata in generated HTML (e.g. title),
metadata=True,
h1=True # include title as H1 at the top of the doc
)
htmlFile = cleaner.clean()
basename = os.path.basename(htmlFile)
title = basename.replace(".html", "")
os.remove(htmlFile)
else:
title = self.title
# CONVERT TO PDF WITH ELECTON PDF
url = self.url
pdfPath = self.folderpath + "/" + title + self.append + ".pdf"
electron = self.settings["executables"]["electron path"]
cmd = """%(electron)s -i "%(url)s" -o "%(pdfPath)s" --printBackground """ % locals()
p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
stdout, stderr = p.communicate()
self.log.debug('output: %(stdout)s' % locals())
if len(stderr):
print stderr
exists = os.path.exists(pdfPath)
if not exists:
print "%(pdfPath)s was not generated for some reason - please investigate" % locals()
sys.exit(0)
self.log.info('completed the ``_print_original_webpage`` method')
return pdfPath
def _print_parsed_webpage(self):
"""*print the parsed/cleaned webpage*
**Return:**
- ``pdfPath`` -- the path to the generated PDF
"""
self.log.debug('starting the ``_print_parsed_webpage()`` method')
from polyglot import htmlCleaner
cleaner = htmlCleaner(
log=self.log,
settings=self.settings,
url=self.url,
outputDirectory=self.folderpath,
title=self.title, # SET TO FALSE TO USE WEBPAGE TITLE,
style=True, # add polyglot's styling to the HTML document
metadata=True, # include metadata in generated HTML (e.g. title),
h1=True # include title as H1 at the top of the doc
)
htmlFile = cleaner.clean()
if not htmlFile:
return
pdfPath = htmlFile.replace(".html", self.append + ".pdf")
# CONVERT TO PDF WITH ELECTON PDF
electron = self.settings["executables"]["electron path"]
cmd = """%(electron)s -i "%(htmlFile)s" -o "%(pdfPath)s" """ % locals()
p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
stdout, stderr = p.communicate()
if len(stderr):
print stderr
self.log.debug('output: %(stdout)s' % locals())
# REMOVE HTML FILE
os.remove(htmlFile)
exists = os.path.exists(pdfPath)
if not exists:
print "%(pdfPath)s was not generated for some reason - please investigate" % locals(
)
sys.exit(0)
self.log.debug('completed the ``_print_parsed_webpage()`` method')
return pdfPath
