diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-06-23 23:15:41 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-23 23:15:41 -0700 |
commit | 1aea4911bf336570a1b6b32d75eced523c329ed6 (patch) | |
tree | dd479e2207b74a0b1450a34ab166c1a8cb98d062 /notes/longtail_crawl.txt | |
parent | 4018c62adc32a88a76f7bd54f1003d58a29fe120 (diff) | |
download | chocula-1aea4911bf336570a1b6b32d75eced523c329ed6.tar.gz chocula-1aea4911bf336570a1b6b32d75eced523c329ed6.zip |
update notes about longtail homepage URLs
Diffstat (limited to 'notes/longtail_crawl.txt')
-rw-r--r-- | notes/longtail_crawl.txt | 41 |
1 files changed, 38 insertions, 3 deletions
diff --git a/notes/longtail_crawl.txt b/notes/longtail_crawl.txt index 9d2fe96..20cdad3 100644 --- a/notes/longtail_crawl.txt +++ b/notes/longtail_crawl.txt @@ -1,11 +1,47 @@ +## 2020 Crawl Query + .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; + FROM homepage + LEFT JOIN journal ON homepage.issnl = journal.issnl + WHERE + (homepage.terminal_status_code = 200 or homepage.blocked or homepage.terminal_status_code is null) + 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 homepage.domain != 'oclc.org' + AND homepage.host != 'www.ncbi.nlm.nih.gov' + AND homepage.domain != 'umi.com' + AND homepage.domain != 'doi.org' + AND homepage.host != 'www.thefreelibrary.com' + AND (journal.is_longtail = 1 + OR journal.publisher_type = 'society' + OR journal.publisher_type = 'unipress' + OR journal.publisher_type IS NULL) + AND (journal.has_dois = 0 or journal.release_count < 20); + +## Older 2019 Crawl Query + + .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 @@ -13,7 +49,6 @@ 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; |