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

use file with links as arguments

Browse Source
This commit is contained in:
Maks Snegov 2014-07-20 13:48:18 +04:00
parent 514b39d287
commit 5c9d04cf3d
1 changed files with 23 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
nevernote.py
View File

@ -126,6 +126,22 @@ def complete_url(url, base_url):
return url return url
def process_url(url):
print('Processing URL: %s' % url)
try:
url_duplicate(url)
except UrlDuplicateError as e:
print(e)
return
page = get_text(url)
parser = TitleParser(strict=False)
parser.feed(page)
page = embed_pictures(page, parser.images, base_url=url)
page = embed_css(page, parser.css, base_url=url)
write_file(page, parser.title, comment=url)
def main(): def main():
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description='Nevernote - download pages locally.') description='Nevernote - download pages locally.')
@ -133,19 +149,13 @@ def main():
help='URL of page to download') help='URL of page to download')
args = parser.parse_args() args = parser.parse_args()
for url in args.urls: for arg in args.urls:
try: if os.path.isfile(arg):
url_duplicate(url) print('Found file %s' % arg)
except UrlDuplicateError as e: for url in (line.strip() for line in open(arg)):
print(e) process_url(url)
continue else:
page = get_text(url) process_url(arg)
parser = TitleParser(strict=False)
parser.feed(page)
page = embed_pictures(page, parser.images, base_url=url)
page = embed_css(page, parser.css, base_url=url)
write_file(page, parser.title, comment=url)
if __name__ == '__main__': if __name__ == '__main__':