aboutsummaryrefslogtreecommitdiffstats
path: root/notes/longtail_crawl.txt
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2020-06-23 20:10:46 -0700
committerBryan Newbold <bnewbold@archive.org>2020-06-23 20:10:46 -0700
commit4be1ec0cdb382d7b545eeb4c451cc123d9199d95 (patch)
treee1e8131e2caef749496dbda8b83f355ac296d6ce /notes/longtail_crawl.txt
parent05f6a1b143a521688ccb3a59f300b44f5c04c6be (diff)
downloadchocula-4be1ec0cdb382d7b545eeb4c451cc123d9199d95.tar.gz
chocula-4be1ec0cdb382d7b545eeb4c451cc123d9199d95.zip
commit notes and issnl_prefix.py helper script
Diffstat (limited to 'notes/longtail_crawl.txt')
-rw-r--r--notes/longtail_crawl.txt21
1 files changed, 21 insertions, 0 deletions
diff --git a/notes/longtail_crawl.txt b/notes/longtail_crawl.txt
new file mode 100644
index 0000000..9d2fe96
--- /dev/null
+++ b/notes/longtail_crawl.txt
@@ -0,0 +1,21 @@
+
+ .mode tabs
+ .output longtail_homepage_urls.tsv
+
+ SELECT homepage.url, homepage.issnl
+ FROM homepage LEFT JOIN journal ON homepage.issnl = journal.issnl
+ WHERE homepage.terminal_status_code = 200 AND journal.is_longtail = 1 AND homepage.domain != 'archive.org' AND homepage.host NOT LIKE '%scielo%' AND homepage.domain != 'jst.go.jp' AND homepage.host != 'books.google.com' AND homepage.host != 'www.google.com' AND journal.has_dois = 0;
+
+
+## Test Queries
+
+ SELECT count(distinct homepage.issnl) FROM homepage LEFT JOIN journal ON homepage.issnl = journal.issnl WHERE homepage.terminal_status_code = 200 AND journal.is_longtail = 1;
+
+ SELECT ... FROM homepage LEFT JOIN journal ON homepage.issnl = journal.issnl WHERE homepage.terminal_status_code = 200 AND journal.is_longtail = 1;
+
+
+ SELECT homepage.domain, COUNT(*) FROM homepage LEFT JOIN journal ON homepage.issnl = journal.issnl WHERE homepage.terminal_status_code = 200 AND journal.is_longtail = 1 AND homepage.domain != 'archive.org' AND homepage.host NOT LIKE '%scielo%' AND homepage.domain != 'jst.go.jp' AND homepage.host != 'books.google.com' AND homepage.host != 'www.google.com' AND journal.has_dois = 0
+ GROUP BY homepage.domain ORDER BY COUNT(*) DESC LIMIT 20;
+
+ SELECT homepage.suffix , COUNT(*) FROM homepage LEFT JOIN journal ON homepage.issnl = journal.issnl WHERE homepage.terminal_status_code = 200 AND journal.is_longtail = 1 AND homepage.domain != 'archive.org'
+ GROUP BY homepage.suffix ORDER BY COUNT(*) DESC LIMIT 20;