id
type
0
status
20
review version
0
cleanup version
0
pending deletion
0
created at
2025-08-26 22:16:02
updated at
2025-08-26 22:16:02
url
https://nekrologi.wyborcza.pl/0,18,,,4,OBITUARY,AC%5BGD%5DID%5B2021-01-15+TO+2021-01-15%5D,false.html
url length
101
url crc
40826
url crc32
3902840698
location type
1
canonical status
2
canonical page id
-
domain id
domain tld
616
domain parts
0
originating warc id
-
originating url
https://data.commoncrawl.org/crawl-data/CC-MAIN-2025-33/segments/1754151579063.98/warc/CC-MAIN-20250815204238-20250815234238-00285.warc.gz
source type
11
block type
0
extracted fields
24
extracted bits
–
detected location
0
detected language
121 (Polish)
category id
-
index version
1
paywall score
0
spam phrases
0
text nonlatin
0
text cyrillic
0
text characters
2729
text words
525
text unique words
228
text lines
121
text sentences
40
text paragraphs
0
text words per sentence
13
text matched phrases
0
text matched dictionaries
0
links self subdomains
0
links other subdomains
1
links other domains
2
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
15
links ext leaks
0
links ext ugc
0
links ext klim
0
links ext generic
0