diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2021-06-02 01:39:20 +0200 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2021-06-02 01:39:20 +0200 |
| commit | 5f44c236f82d3d02f9dd0061f0a0ab3d8010a3f5 (patch) | |
| tree | c7e44415ab45e3f2e5ee27a8d139e833f78fdd10 | |
| parent | 60dfd396a815705e4e6a52fb9321837f43ed2fc1 (diff) | |
| download | refcat-5f44c236f82d3d02f9dd0061f0a0ab3d8010a3f5.tar.gz refcat-5f44c236f82d3d02f9dd0061f0a0ab3d8010a3f5.zip | |
tasks: cleanup url list
| -rw-r--r-- | extra/refurls/README.md | 3 | ||||
| -rw-r--r-- | python/refcat/tasks.py | 2 |
2 files changed, 4 insertions, 1 deletions
diff --git a/extra/refurls/README.md b/extra/refurls/README.md new file mode 100644 index 0000000..81ddd19 --- /dev/null +++ b/extra/refurls/README.md @@ -0,0 +1,3 @@ +# URLs found in References + + diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 7c1fabc..4eefdcc 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -278,7 +278,7 @@ class URLList(Refcat): cut -f 3 | skate-cleanup -X -c url -B -S -f 1 | LC_ALL=C sort -u -T {tmpdir} -k1,1 -S25% --parallel 4 | - LC_ALL=C grep ^http | + LC_ALL=C grep -E 'https?://' zstd -T0 -c > {output} """, n=self.n, |