simon987/opendirectories-bot
1
0
Fork 0
mirror of https://github.com/simon987/opendirectories-bot.git synced 2025-04-19 18:26:44 +00:00
Code Issues Projects Releases Wiki Activity

Fixes problem with link tags with no href

Browse Source
This commit is contained in:
simon 2018-02-14 14:23:31 -05:00
parent 56b28f534e
commit 90c5835cb5
1 changed files with 41 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
parser.py
View File

@ -136,6 +136,7 @@ class NginxParser(PageParser):
try: try:
if PageParser.should_save_link(link.text): if PageParser.should_save_link(link.text):
target = link.get("href") target = link.get("href")
if target is not None:
short_file_name = os.path.split(target)[1] short_file_name = os.path.split(target)[1]
full_link = urljoin(base_url, target) full_link = urljoin(base_url, target)
file_type = PageParser.file_type(target) file_type = PageParser.file_type(target)
@ -188,6 +189,7 @@ class ApacheParser(PageParser):
if PageParser.should_save_link(link.text): if PageParser.should_save_link(link.text):
target = link.get("href") target = link.get("href")
if target is not None:
short_file_name = os.path.split(target)[1] short_file_name = os.path.split(target)[1]
file_type = PageParser.file_type(target) file_type = PageParser.file_type(target)
full_link = urljoin(base_url, target) full_link = urljoin(base_url, target)
@ -210,6 +212,7 @@ class ApacheParser(PageParser):
if PageParser.should_save_link(link.text): if PageParser.should_save_link(link.text):
target = link.get("href") target = link.get("href")
if target is not None:
short_file_name = os.path.split(target)[1] short_file_name = os.path.split(target)[1]
full_link = urljoin(base_url, target) full_link = urljoin(base_url, target)
file_type = PageParser.file_type(target) file_type = PageParser.file_type(target)