diff --git a/lib/eml2html.py b/lib/eml2html.py
index ed65727..ac23b4a 100644
--- a/lib/eml2html.py
+++ b/lib/eml2html.py
@@ -78,10 +78,9 @@ def __get_formatted_header_info(self):
for header in FORMATTED_HEADERS_TO_INCLUDE:
if self.eml[header]:
decoded_string = self.__get_utf8_header(self.eml[header])
- header_info = header_info + '' + header + ': '\
- + decoded_string + '
'
+ header_info = f'{header_info}{header}: {decoded_string}
'
- return header_info + '
'
+ return f'{header_info}
'
def __get_utf8_header(self, header):
# There is a simpler way of doing this here:
@@ -89,13 +88,12 @@ def __get_utf8_header(self, header):
# seem to work, as it inserts a space between certain elements
# in the string that's not warranted/correct.
decoded_header = decode_header(header)
- hdr = ""
- for element in decoded_header:
- if isinstance(element[0], bytes):
- hdr += str(element[0], element[1] or 'ASCII')
- else:
- hdr += element[0]
- return hdr
+ return "".join(
+ str(element[0], element[1] or 'ASCII')
+ if isinstance(element[0], bytes)
+ else element[0]
+ for element in decoded_header
+ )
def __cid_replace(self, matchobj):
cid = matchobj.group(1)
@@ -110,7 +108,7 @@ def __cid_replace(self, matchobj):
image_base64 = re.sub("[\r\n\t]", "", image_base64)
image_decoded = image_part.get_payload(decode=True)
mime_type = self.__get_mime_type(image_decoded)
- return "data:" + mime_type + ";base64," + image_base64
+ return f"data:{mime_type};base64,{image_base64}"
# else:
# raise FatalException(
# "Could not find image cid " + cid + " in email content.")
@@ -141,16 +139,24 @@ def __find_part_by_content_type_name(self, message, content_type_name):
return None
def __find_part_by_content_id(self, message, content_id):
- for part in message.walk():
- if part['Content-ID'] in (content_id, '<' + content_id + '>'):
- return part
- return None
+ return next(
+ (
+ part
+ for part in message.walk()
+ if part['Content-ID'] in (content_id, f'<{content_id}>')
+ ),
+ None,
+ )
def __part_by_content_type(self, message, content_type):
- for part in message.walk():
- if part.get_content_type() == content_type:
- return part
- return None
+ return next(
+ (
+ part
+ for part in message.walk()
+ if part.get_content_type() == content_type
+ ),
+ None,
+ )
def __remove_invalid_urls(self, payload):
soup = BeautifulSoup(payload, "html5lib")
@@ -162,16 +168,14 @@ def __remove_invalid_urls(self, payload):
if lower_src == 'broken':
del img['src']
elif not lower_src.startswith('data'):
- found_blacklist = False
-
- for image_load_blacklist_item in IMAGE_LOAD_BLACKLIST:
- if image_load_blacklist_item in lower_src:
- found_blacklist = True
-
- if not found_blacklist:
- if not utils.can_url_fetch(src):
- del img['src']
- else:
+ found_blacklist = any(
+ image_load_blacklist_item in lower_src
+ for image_load_blacklist_item in IMAGE_LOAD_BLACKLIST
+ )
+ if (
+ not found_blacklist
+ and not utils.can_url_fetch(src)
+ or found_blacklist
+ ):
del img['src']
-
return str(soup)
diff --git a/lib/html2img.py b/lib/html2img.py
index 06e3005..39d0fa8 100644
--- a/lib/html2img.py
+++ b/lib/html2img.py
@@ -45,9 +45,7 @@ def __get_unique_version(self, filename):
counter = 1
file_name_parts = os.path.splitext(filename)
while os.path.isfile(filename):
- filename = "%s_%s%s" % (file_name_parts[0],
- '_' + str(counter),
- file_name_parts[1])
+ filename = f"{file_name_parts[0]}__{str(counter)}{file_name_parts[1]}"
counter += 1
return filename
@@ -61,7 +59,7 @@ def __process_errors(self, ret_code, error):
original_error = str(error, 'utf-8').rstrip()
stripped_error = stripped_error.rstrip()
- if ret_code > 0 and original_error == '':
+ if ret_code > 0 and not original_error:
raise FatalException("wkhtmltoimage failed with exit code " +
str(ret_code) +
", no error output.")
diff --git a/lib/html2pdf.py b/lib/html2pdf.py
index b260a7d..77a108d 100644
--- a/lib/html2pdf.py
+++ b/lib/html2pdf.py
@@ -43,9 +43,7 @@ def __get_unique_version(self, filename):
counter = 1
file_name_parts = os.path.splitext(filename)
while os.path.isfile(filename):
- filename = "%s_%s%s" % (file_name_parts[0],
- '_' + str(counter),
- file_name_parts[1])
+ filename = f"{file_name_parts[0]}__{str(counter)}{file_name_parts[1]}"
counter += 1
return filename
@@ -59,7 +57,7 @@ def __process_errors(self, ret_code, error):
original_error = str(error, 'utf-8').rstrip()
stripped_error = stripped_error.rstrip()
- if ret_code > 0 and original_error == '':
+ if ret_code > 0 and not original_error:
raise FatalException("wkhtmltopdf failed with exit code " +
str(ret_code) +
", no error output.")
diff --git a/lib/utils.py b/lib/utils.py
index b53bf65..5485fae 100644
--- a/lib/utils.py
+++ b/lib/utils.py
@@ -6,11 +6,6 @@ def can_url_fetch(src):
try:
req = Request(src)
urlopen(req)
- except HTTPError:
+ except (HTTPError, URLError, ValueError):
return False
- except URLError:
- return False
- except ValueError:
- return False
-
return True
diff --git a/test.py b/test.py
index 6d85dd3..6a5089e 100644
--- a/test.py
+++ b/test.py
@@ -20,15 +20,13 @@ def __init__(self, IMAP_SERVER, EMAIL_ADDRESS,
self.mail.select()
def get_emails(self):
- uids = self.mail.uid('SEARCH', 'ALL')[1][0].split()
- return uids
+ return self.mail.uid('SEARCH', 'ALL')[1][0].split()
def get_email_message(self, email_id):
_, data = self.mail.uid('FETCH', email_id, '(RFC822)')
raw_email = data[0][1]
raw_email_string = raw_email.decode('utf-8')
- email_message = email.message_from_string(raw_email_string)
- return email_message
+ return email.message_from_string(raw_email_string)
email_helper = EmailHelper(IMAP_SERVER, EMAIL_ADDRESS,
@@ -45,12 +43,12 @@ def get_email_message(self, email_id):
email_message = email_helper.get_email_message(uid)
html = email_to_html_convertor.convert(email_message)
- filename = uid.decode() + ".jpg"
+ filename = f"{uid.decode()}.jpg"
img_path = html_to_img_convertor.save_img(
html.encode(), output_dir, filename)
print(img_path)
- filename = uid.decode() + ".pdf"
+ filename = f"{uid.decode()}.pdf"
pdf_path = html_to_pdf_convertor.save_pdf(
html.encode(), output_dir, filename)
print(pdf_path)