aboutsummaryrefslogtreecommitdiffstats
path: root/pig/tests/files/papers_domain_words.cdx
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-07 22:10:51 -0700
committerBryan Newbold <bnewbold@archive.org>2018-05-07 22:11:18 -0700
commitd1401444dbfb515e62094f873d520a23ccbc29d9 (patch)
tree418a21b93261230b006127107b124e5c12236ab7 /pig/tests/files/papers_domain_words.cdx
parent81d2f6290fff487f0f49b109227443c0f8a7aedb (diff)
downloadsandcrawler-d1401444dbfb515e62094f873d520a23ccbc29d9.tar.gz
sandcrawler-d1401444dbfb515e62094f873d520a23ccbc29d9.zip
pig script to filter GWB CDX by SURT regexes
Diffstat (limited to 'pig/tests/files/papers_domain_words.cdx')
-rw-r--r--pig/tests/files/papers_domain_words.cdx11
1 files changed, 11 insertions, 0 deletions
diff --git a/pig/tests/files/papers_domain_words.cdx b/pig/tests/files/papers_domain_words.cdx
new file mode 100644
index 0000000..48e2313
--- /dev/null
+++ b/pig/tests/files/papers_domain_words.cdx
@@ -0,0 +1,11 @@
+#http://research.fit.edu/sealevelriselibrary/documents/doc_mgr/448/Florida_Keys_Low_Island_Biodiversity_&_SLR_-_Ross_et_al_2009.pdf
+#http://ijs.sgmjournals.org:80/cgi/reprint/54/6/2217.pdf
+#http://eprints.ecs.soton.ac.uk/12020/1/mind-the-semantic-gap.pdf
+#http://eprint.uq.edu.au/archive/00004120/01/R103_Forrester_pp.pdf
+
+# should match 4:
+
+edu,fit,research)/sealevelriselibrary/documents/doc_mgr/448/Florida_Keys_Low_Island_Biodiversity_&_SLR_-_Ross_et_al_2009.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+org,sgmjournals,ijs)//cgi/reprint/54/6/2217.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+uk,ac,soton,ecs,eprints)/12020/1/mind-the-semantic-gap.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz
+au,edu,uq,eprint)/archive/00004120/01/R103_Forrester_pp.pdf 20170706005950 http://mit.edu/file.pdf application/pdf 200 MQHD36X5MNZPWFNMD5LFOYZSFGCHUN3V - - 123 456 CRAWL/CRAWL.warc.gz