id
type
0
status
30
review version
0
cleanup version
0
pending deletion
0
created at
2025-11-10 09:25:02
updated at
2025-11-10 09:25:02
url
https://www.alesis.com/?URL=https%3A%2F%2Fckan-dlsc-dev.unl.edu%2Fuploads%2Fuser%2F2022-12-06-222831.627037INFO-SLOT-PRAGMATIC-GACOR.html
url length
137
url crc
29069
url crc32
2999284109
location type
1
canonical status
2
canonical page id
-
domain id
domain tld
2211
domain parts
0
originating warc id
-
originating url
https://data.commoncrawl.org/crawl-data/CC-MAIN-2025-33/segments/1754151280053.88/warc/CC-MAIN-20250808223431-20250809013431-00572.warc.gz
source type
11
block type
0
extracted fields
8
extracted bits
title
detected location
0
detected language
1 (English)
category id
227
index version
2025123101
paywall score
0
spam phrases
0
text nonlatin
0
text cyrillic
0
text characters
1611
text words
271
text unique words
141
text lines
97
text sentences
7
text paragraphs
1
text words per sentence
38
text matched phrases
2
text matched dictionaries
2
links self subdomains
0
links other subdomains
7
links other domains
25
links spam adult
0
links spam random
0
links spam expired
0
links ext activities
0
links ext ecommerce
0
links ext finance
0
links ext crypto
0
links ext booking
0
links ext news
0
links ext leaks
0
links ext ugc
0
links ext klim
0
links ext generic
0
image author
featured image