acdha

#!/usr/bin/env phantomjs --disk-cache=false
/*
    Load one or more URLs requesting Akamai CDN diagnostic information for every resource
    and list resources which are configured not to be cached:

    phantomjs check-akamai-status.js https://www.microsoft.com/ http://www.state.gov https://www.wdl.org/en/

    Additional timing information will be displayed to easily distinguish between requests
    made before DOMContentLoaded or the full load event.
*/

acdha

#!/bin/bash

python pwb.py replace.py -simulate \
    -catr:World_Digital_Library \
    -always \
    -summary:'Convert wdl.org links to use HTTPS' \
    'http://www.wdl.org' 'https://www.wdl.org'  \
    'http://content.wdl.org' 'https://content.wdl.org'  \
    'http://wdl.org' 'https://www.wdl.org'  \
    '{{URL|www.wdl.org}}' '{{URL|https://www.wdl.org}}'  \

acdha

http://content.wdl.org/274/service/274.pdf
http://content.wdl.org/5587/service/thumbnail/1430167600/1024x1024/1/1.jpg
http://content.wdl.org/7380/service/7380.pdf
http://www.wdl.org/
http://www.wdl.org/ar
http://www.wdl.org/ar/
http://www.wdl.org/ar/item/10079
http://www.wdl.org/ar/item/10085
http://www.wdl.org/ar/item/10087
http://www.wdl.org/ar/item/10092/

acdha

"POT-Creation-Date: 2015-12-09 15:27+0000\n"
"PO-Revision-Date: 2015-11-26 00:54+0000\n"
"Language: ar\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Plural-Forms: nplurals=6; plural=n==0 ? 0 : n==1 ? 1 : n==2 ? 2 : n%100>=3 "
"&& n%100<=10 ? 3 : n%100>=11 && n%100<=99 ? 4 : 5;\n"

msgid "IIIF Manifest"

acdha

#!/usr/bin/env python3
# encoding: utf-8
"""Lorem ipsum dolor sit amet


Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et
dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea
commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat
nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit
anim id est laborum.

acdha

11/27/15 1:22:46.215 PM Dropbox[26351]: Dropbox(26351,0xa3778000) malloc: *** mach_vm_map(size=4198400) failed (error code=3)
*** error: can't allocate region
*** set a breakpoint in malloc_error_break to debug
11/27/15 1:22:46.253 PM Dropbox[26351]: 70  Dropbox                             0x00001868 start + 40
69  Dropbox                             0x0000193d start + 253
68  Dropbox                             0x00002093 main + 1427
67  Dropbox                             0x00004264 main + 10084
66  Python                              0x046db158 PyRun_SimpleFile + 40
65  Python                              0x046d9753 PyRun_SimpleFileExFlags + 755
64  Python                              0x046b2ee7 PyEval_EvalCode + 87

acdha

Opening https://authorities.loc.gov/ (0 remaining)
	💻 DOMContentLoaded 0.145s
	💻 load 0.489s
✅  https://authorities.loc.gov/
… done!
Opening https://catalog.loc.gov/ (0 remaining)
	💻 DOMContentLoaded 0.079s
	💻 load 0.362s
✅  https://catalog.loc.gov/
… done!

acdha

http://catalog2.loc.gov/cgi-bin/Pwebrecon.cgi?DB=local&BBID=18724967&v3=1
http://catalog2.loc.gov/cgi-bin/Pwebrecon.cgi?DB=local&PAGE=First
http://chroniclingamerica.loc.gov/
http://findingaids.loc.gov/
http://read.gov/
http://www.copyright.gov/
http://www.loc.gov/
http://www.loc.gov/about/office-of-the-inspector-general/
http://www.loc.gov/accessibility/
http://www.loc.gov/accessibility/web-site-accessibility/

acdha

Crawling https://www.usa.gov/
✅  https://www.usa.gov/
Crawling https://www.read.gov/cfb/
❌  https://www.read.gov/cfb/
Crawling https://www.read.gov/
❌  https://www.read.gov/
Crawling https://www.loc.gov/websites/
✅  https://www.loc.gov/websites/
Crawling https://www.loc.gov/vets/
✅  https://www.loc.gov/vets/

acdha

<?xml version="1.0"?>
<ruleset name="LibraryOfCongress">
    <target host="loc.gov"/>
    <target host="www.loc.gov"/>
    <target host="congress.gov"/>
    <target host="memory.loc.gov"/>
    <target host="lcweb2.loc.gov"/>
    <target host="catalog.loc.gov"/>
    <target host="catalog2.loc.gov"/>
    <target host="cdn.loc.gov"/>