Feed date scraper for Gemini (protocol)
getdesc: improve tolerance of link line parsing
Zach DeCook 2021-02-17
parent 84f4b0b · commit a9df2bb
-rwxr-xr-xtest_zachwalk.py1
-rwxr-xr-xzachwalk.py2
2 files changed, 2 insertions, 1 deletions
diff --git a/test_zachwalk.py b/test_zachwalk.py
index 42efc43..0411e1f 100755
--- a/test_zachwalk.py
+++ b/test_zachwalk.py
@@ -9,6 +9,7 @@ def main():
assert zachwalk.gnd([b'=> 2020/11/25/hello-gemini.gmi 2020-11-25 - Hello, Gemini!']) == parse('2020-11-25').date()
assert zachwalk.gnd([b'=> gemini://drewdevault.com/2020/09/21/Gemini-TOFU.gmi September 21, 2020: TOFU recommendations for Gemini']) == parse('2020-09-21').date()
assert zachwalk.gnd(['=> gemini://drewdevault.com/2021/02/15/Status-update-February-2021.gmi February 15, 2021: Status update, February 2021']) == parse('2021-02-15').date()
+ assert zachwalk.gnd(['=>2021-01-28.gmi 2021-01-28 - RE ew0k: Your Gemini Browser and Server are Probably Doing Certificates Wrong']) == parse('2021-01-28').date()
if __name__ == '__main__':
main()
diff --git a/zachwalk.py b/zachwalk.py
index 1a15ddc..9df813c 100755
--- a/zachwalk.py
+++ b/zachwalk.py
@@ -70,7 +70,7 @@ def isAbsGeminiUrl(url):
return url[0:9] == 'gemini://'
def getdesc(line):
- return ' '.join(line.split(' ')[2:]).strip()
+ return ' '.join(line[2:].strip().split(' ')[1:])
if __name__ == '__main__':
main()