id
type
0
status
20
review version
0
cleanup version
0
pending deletion
0
created at
2025-08-25 05:40:21
updated at
2025-08-25 05:40:22
url
https://www.vigilantfox.com/p/usda-preparing-to-mass-vaccinate?open=false
url length
73
url crc
26840
url crc32
219506904
location type
1
canonical status
30
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/1754151579063.98/warc/CC-MAIN-20250815204238-20250815234238-00740.warc.gz
source type
11
block type
0
extracted fields
36
extracted bits
–
detected location
0
detected language
1 (English)
category id
-
index version
1
paywall score
0
spam phrases
0
text nonlatin
0
text cyrillic
0
text characters
3786
text words
721
text unique words
373
text lines
129
text sentences
35
text paragraphs
10
text words per sentence
20
text matched phrases
0
text matched dictionaries
0
links self subdomains
0
links other subdomains
5
links other domains
5
links spam adult
0
links spam random
0
links spam expired
0
links ext activities
1
links ext ecommerce
0
links ext finance
0
links ext crypto
0
links ext booking
0
links ext news
2
links ext leaks
0
links ext ugc
12
links ext klim
0
links ext generic
0