snegov/nevernote
1
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

Refactor code

Browse Source
This commit is contained in:
Maks Snegov 2019-10-22 11:43:54 +03:00
parent 44b8a17841
commit 91cddfab7c
1 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
nevernote.py
View File

@ -10,8 +10,6 @@ from urllib.parse import urlparse
import requests import requests
class UrlDuplicateError(Exception): pass
URLDUP = re.compile(r'^<!-- URL: (.*) -->$') URLDUP = re.compile(r'^<!-- URL: (.*) -->$')
@ -48,8 +46,8 @@ def get_text(url):
return response.text return response.text
def embedded_image(url): def get_embedded_binary(url):
'''Download content from URL and return bytes if target is image''' """Download content from URL and return bytes if target is image"""
response = requests.get(url) response = requests.get(url)
response.raise_for_status() response.raise_for_status()
ctype = response.headers.get('Content-Type') ctype = response.headers.get('Content-Type')
@ -59,17 +57,19 @@ def embedded_image(url):
def embed_pictures(page, pict_urls, base_url=None): def embed_pictures(page, pict_urls, base_url=None):
"""Write all pictures in HTML file"""
for url in pict_urls: for url in pict_urls:
print('New picture: %s' % url) print('New picture: %s' % url)
try: try:
page = page.replace( page = page.replace(
url, embedded_image(complete_url(url, base_url))) url, get_embedded_binary(complete_url(url, base_url)))
except requests.exceptions.HTTPError: except requests.exceptions.HTTPError:
pass pass
return page return page
def embed_css(page, css_urls, base_url=None): def embed_css(page, css_urls, base_url=None):
"""Write all CSS's in HTML file"""
for url in css_urls: for url in css_urls:
if not url: if not url:
continue continue
@ -83,18 +83,20 @@ def embed_css(page, css_urls, base_url=None):
def embed_scripts(page, script_urls, base_url=None): def embed_scripts(page, script_urls, base_url=None):
"""Write all scripts in HTML file"""
for url in script_urls: for url in script_urls:
print('New script: %s' % url) print('New script: %s' % url)
try: try:
page = page.replace( page = page.replace(
url, embedded_image(complete_url(url, base_url))) url, get_embedded_binary(complete_url(url, base_url)))
except requests.exceptions.HTTPError: except requests.exceptions.HTTPError:
pass pass
return page return page
def url_duplicate(url): def url_duplicate(url):
for htmlfile in os.listdir(): """Check if url was already downloaded"""
for htmlfile in os.listdir(path='.'):
if not htmlfile.endswith('.html'): if not htmlfile.endswith('.html'):
continue continue
with open(htmlfile) as h: with open(htmlfile) as h:
@ -105,6 +107,7 @@ def url_duplicate(url):
def write_file(page, title, comment=None): def write_file(page, title, comment=None):
"""Save HTML to file on a disk"""
write_inc = lambda i: '_%d' % i if i > 1 else '' write_inc = lambda i: '_%d' % i if i > 1 else ''
inc = 0 inc = 0
while True: while True:
@ -120,7 +123,8 @@ def write_file(page, title, comment=None):
a_file.write(page) a_file.write(page)
def complete_url(url, base_url): def complete_url(url, base_url=None):
"""Create absolute URL from relative paths"""
base_up = urlparse(base_url) base_up = urlparse(base_url)
if base_url is not None: if base_url is not None:
up = urlparse(url) up = urlparse(url)
@ -132,6 +136,7 @@ def complete_url(url, base_url):
def process_url(url): def process_url(url):
"""Save single URL to a file"""
print('Processing URL: %s' % url) print('Processing URL: %s' % url)
try: try:
url_duplicate(url) url_duplicate(url)
@ -170,5 +175,9 @@ def main():
process_url(arg) process_url(arg)
class UrlDuplicateError(Exception):
pass
if __name__ == '__main__': if __name__ == '__main__':
sys.exit(main()) sys.exit(main())