National Science Foundation - Internet Archive research 2013-2018 Prof. Matthew Weber Hai Nguyen Technical support: Eric Marshall, Kristina Plazonic, Ben Bakelaar Rutgers University, School of Communication and Information ******************* External links to source data and resources: The Internet Archive (http://www.archive.org) - the largest Internet archive in the world, and a source for much of the data in this project Archives Unleashed (http://www.archivesunleashed.org) - a useful resource with tools for accessing raw data ******************* BATCH 2 (2018) DATA SETS /earlyweb /house /senate INPUT DATA ARC file format http://archive.org/web/researcher/ArcFileFormat.php WARC file format https://www.loc.gov/preservation/digital/formats/fdd/fdd000236.shtml Processed with Sparq/Scala script developed by Kristina Plazonic Senate and house dataset links were provided raw due to most links being internal (same SLD) OUTPUT DATA 1 Source URL (only SLD, no pages/sub-directories) 2 Target URL (same as above) 3 Date (YYYYMMDD) 4 Sum of content length 5 # of links EARLYWEB SET EARLYWEB_1996_2000_part01.tar EARLYWEB_1996_2000_part02.tar EARLYWEB_1996_2000_part03.tar EARLYWEB_1996_2000_part04.tar EARLYWEB_1996_2000_part05.tar EARLYWEB_1996_2000_part06.tar EARLYWEB_1996_2000_part07.tar EARLYWEB_1996_2000_part08.tar EARLYWEB_1996_2000_part09.tar EARLYWEB_1996_2000_part10.tar EARLYWEB_1996_2000_part11.tar EARLYWEB_1996_2000_part12.tar EARLYWEB_1996_2000_part13.tar EARLYWEB_1996_2000_part14.tar EARLYWEB_1996_2000_part15.tar EARLYWEB_1996_2000_part16.tar HOUSE SET HOUSE_2009_part01.tar.gz HOUSE_2009_part02.tar.gz HOUSE_2009_part03.tar.gz HOUSE_2009_part04.tar.gz HOUSE_2009_part05.tar.gz HOUSE_2009_part06.tar.gz HOUSE_2009_part07.tar.gz HOUSE_2009_part08.tar.gz SENATE SET SENATE_2009_part01.tar.gz SENATE_2009_part02.tar.gz SENATE_2009_part03.tar.gz ******************* SAMPLE ARC FILE FORMAT HEADER (JSON) { "Envelope":{ "Format":"ARC", "ARC-Header-Metadata":{ "Date":"20130724000000", "Content-Length":"76", "Content-Type":"text/plain", "Target-URI":"filedesc://NSF-HOUSEGOV-2006-2012-EXTRACTION-PART-00222-000109.arc.gz", "IP-Address":"0.0.0.0" }, "ARC-Header-Length":"107", "Payload-Metadata":{ "Trailing-Slop-Length":"1", "Actual-Content-Type":"alexa/filedesc", "Block-Digest":"sha1:KRKKRWMWT3AKLJMKNCQ7ROCGWVDA4YRV", "Actual-Content-Length":"76", "Filedesc-Metadata":{ "Format":"URL IP-address Archive-date Content-type Archive-length", "Organization":"InternetArchive", "Major-Version":"1", "Minor-Version":"0" } } }, "Container":{ "Compressed":true, "Gzip-Metadata":{ "Footer-Length":"8", "Deflate-Length":"170", "Header-Length":"10", "Inflated-CRC":"1680566000", "Inflated-Length":"184" }, "Offset":"0", "Filename":"NSF-HOUSEGOV-2006-2012-EXTRACTION-PART-00222-000109.arc.gz" } } ******************* SAMPLE WARC FILE FORMAT HEADER (JSON) { "Envelope":{ "Format":"WARC", "WARC-Header-Length":"286", "Block-Digest":"sha1:FJDC7W6E3472YPPWOGPCB42HZPHW54TN", "Actual-Content-Length":"349", "WARC-Header-Metadata":{ "WARC-Type":"warcinfo", "WARC-Filename":"NSF-HOUSEGOV-2006-2012-WARCS-EXTRACTION-PART-00238-000012.warc.gz", "WARC-Date":"2013-07-24T00:00:00.000Z", "Content-Length":"349", "WARC-Record-ID":"", "Content-Type":"application/warc-fields" }, "Payload-Metadata":{ "Trailing-Slop-Length":"4", "Actual-Content-Type":"application/warc-fields", "Actual-Content-Length":"345", "WARC-Info-Metadata":{ "robots":"ignore", "software":"archive-commons-0.0.1-SNAPSHOT-2011-06-28 03:04:05 Extractor", "audience":"NSF Project", "http-header-from":"archive-crawler-agent@lists.sourceforge.net", "http-header-user-agent":"Mozilla/5.0 (compatible; archive.org_bot/1.10.0 +http://www.archives.gov/crawl.html)", "format":"WARC File Format 1.0", "publisher":"Internet Archive" } } }, "Container":{ "Compressed":true, "Gzip-Metadata":{ "Footer-Length":"8", "Deflate-Length":"451", "Header-Length":"10", "Inflated-CRC":"1827023597", "Inflated-Length":"635" }, "Offset":"0", "Filename":"NSF-HOUSEGOV-2006-2012-WARCS-EXTRACTION-PART-00238-000012.warc.gz" } } ******************* File information for SENATE_2009_part01.tar.gz Contains compressed folder "part1", which contains: part-00000-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00001-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00002-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00003-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00004-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00005-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00006-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00007-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00008-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00009-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00010-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00011-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00012-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00013-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00014-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00015-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00016-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00017-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00018-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00019-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00020-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00021-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00022-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00023-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00024-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00025-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00026-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00027-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00028-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00029-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00030-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00031-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00032-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00033-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00034-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00035-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00036-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00037-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00038-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00039-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00040-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00041-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00042-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00043-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00044-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00045-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00046-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00047-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00048-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00049-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00050-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00051-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00052-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00053-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00054-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00055-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00056-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00057-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00058-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00059-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00060-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00061-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00062-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00063-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00064-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00065-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00066-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00067-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00068-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00069-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00070-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part-00071-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv ******************* File information for SENATE_2009_part02.tar.gz: Contains compressed folder "part2": part2/part-00072-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00073-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00074-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00075-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00076-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00077-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00078-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00079-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00080-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00081-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00082-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00083-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00084-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00085-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00086-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00087-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00088-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00089-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00090-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00091-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00092-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00093-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00094-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00095-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00096-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00097-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00098-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00099-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00100-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00101-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00102-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00103-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00104-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00105-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00106-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00107-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00108-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00109-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00110-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00111-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00112-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00113-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00114-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00115-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00116-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00117-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00118-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00119-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00120-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00121-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00122-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00123-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00124-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00125-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00126-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00127-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00128-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00129-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00130-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00131-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00132-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00133-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00134-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00135-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00136-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00137-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00138-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00139-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00140-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00141-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00142-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv part2/part-00143-10e39be2-2df7-4e2f-af5c-20292c0980ef-c000.csv ******************* File information for SENATE_2009_part03.tar.gz: Contains compressed folder "senate_links_from_warc.csv": senate_links_from_warc.csv/_SUCCESS [this file is empty and can be ignored] senate_links_from_warc.csv/part-00000-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00001-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00002-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00003-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00004-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00005-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00006-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00007-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00008-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00009-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00010-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00011-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00012-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00013-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00014-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00015-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00016-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00017-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00018-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00019-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00020-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00021-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00022-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00023-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00024-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00025-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00026-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00027-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00028-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00029-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00030-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00031-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00032-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00033-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00034-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00035-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00036-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00037-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00038-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00039-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00040-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00041-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00042-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00043-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00044-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00045-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00046-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00047-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00048-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00049-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00050-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00051-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00052-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00053-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00054-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00055-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00056-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00057-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00058-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00059-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00060-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00061-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00062-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00063-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00064-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00065-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00066-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00067-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00068-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00069-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00070-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00071-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00072-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00073-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00074-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00075-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00076-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00077-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00078-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00079-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00080-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00081-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00082-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00083-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00084-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00085-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00086-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00087-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00088-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00089-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00090-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00091-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00092-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00093-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00094-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00095-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00096-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv senate_links_from_warc.csv/part-00097-9d224b23-62f2-4f5f-854a-41e68ab8550c-c000.csv