Changeset 1066 for Validate External Links

Timestamp:

Aug 1, 2017, 4:30:24 PM (7 years ago)

Author:

iritscen

Message:

Updating Val to new location of files on oni2.net and slight changes to Archive API.

Location:

Validate External Links

Files:

• Run validate_external_links.command (modified) (1 diff)
• sftp_login.txt (modified) (1 diff)
• validate_external_links.sh (modified) (4 diffs)

Validate External Links/Run validate_external_links.command

@@ -12 +12 @@
 LINKS_ONLINE="http://wiki.oni2.net/w/extlinks.csv"
 EXCEPT_LOCAL="file:///path/to/Validate External Links/exceptions.txt"
-EXCEPT_ONLINE="http://iritscen.oni2.net/wiki/exceptions.txt"
+EXCEPT_ONLINE="http://iritscen.oni2.net/val/exceptions.txt"
 REPORT_DIR="/path/to/ValExtLinks reports"
 UPLOAD_INFO="/path/to/Validate External Links/sftp_login.txt"

Validate External Links/sftp_login.txt

@@ -2 +2 @@
 pw:
 port:52010
-path:http/wiki
+path:http/val

Validate External Links/validate_external_links.sh

@@ -26 +26 @@
 
 # Fixed strings -- see the occurrences of these variables to learn their purpose
-AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3146.0 Safari/537.36"
+AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10.12; rv:54.0) Gecko/20100101 Firefox/54.0"
 ARCHIVE_API="http://archive.org/wayback/available"
 ARCHIVE_GENERIC="https://web.archive.org/web/*"
@@ -32 +32 @@
 CHROME="/Applications/Google Chrome Canary.app/Contents/MacOS/Google Chrome Canary"
 CHROME_SCREENSHOT="screenshot.png"
-CURL_CODES="http://iritscen.oni2.net/wiki/curl_codes.txt"
+CURL_CODES="http://iritscen.oni2.net/val/curl_codes.txt"
 EXPECT_SCRIPT_NAME="val_expect_sftp.txt"
-HTTP_CODES="http://iritscen.oni2.net/wiki/http_codes.txt"
+HTTP_CODES="http://iritscen.oni2.net/val/http_codes.txt"
 MY_WIKI_PAGE="http://wiki.oni2.net/User:Iritscen"
 THIS_DIR=$(cd $(dirname $0); pwd)
@@ -51 +51 @@
 # These arrays tells us which HTTP response codes are OK (good) and which are NG (no good). Pages that
 # return NG codes will not be screenshotted. Remember to update http_codes.txt if you add a new code.
-declare -a OK_CODES=(200 301 302 307 401 405 406 501)
-declare -a NG_CODES=(000 403 404 410 500 503)
+declare -a OK_CODES=(200 301 307 401 405 406 501)
+declare -a NG_CODES=(000 302 403 404 410 500 503)
 
 # Characters not allowed in a URL. Curly braces are sometimes used on the wiki to build a link using
@@ -746 +746 @@
          ARCHIVE_QUERY=$(curl --silent --max-time 10 "$ARCHIVE_API?url=$URL&$ARCHIVE_OK_CODES")
 
-         # Isolate "url" property in response and log it if received...
-         if [[ "$ARCHIVE_QUERY" == *\"url\":* ]]; then
-            SNAPSHOT_URL=${ARCHIVE_QUERY#*\"url\":\"}
-            SNAPSHOT_URL=${SNAPSHOT_URL%\",\"timestamp*}
+         # Isolate "url" property in response and log it if a "closest" snapshot was received...
+         if [[ "$ARCHIVE_QUERY" == *\"closest\":* ]]; then
+            SNAPSHOT_URL=${ARCHIVE_QUERY##*\"url\": \"}
+            SNAPSHOT_URL=${SNAPSHOT_URL%\", \"timestamp*}
             valPrint t "  IA suggests $SNAPSHOT_URL"
             valPrint r "                IA suggests {\field{\*\fldinst{HYPERLINK \"$SNAPSHOT_URL\"}}{\fldrslt $SNAPSHOT_URL}}"