1
Default Layout
Move the mouse over tables & columns to read the comments.
Fk fk_page_site page ref site ( site_id -> id )
site_id
Fk fk_page_page_type page ref page_type ( page_type_code -> code )
page_type_code
Fk fk_page_data_page page_data ref page ( page_id -> id )
page_id
Fk fk_page_data_data_type page_data ref data_type ( data_type_code -> code )
data_type_code
Fk fk_link_page link ref page ( from_page -> id )
from_page
Fk fk_link_page_1 link ref page ( to_page -> id )
to_page
Fk fk_image_page_data image ref page ( page_id -> id )
page_id
page
Table crawldb.page
Pk pk_page_data_id ( id )
id
id * serial
Referred by image ( page_id -> id ) Referred by link ( from_page -> id ) Referred by link ( to_page -> id ) Referred by page_data ( page_id -> id )
idx_page_site_id ( site_id )
site_id
site_id integer
References site ( site_id -> id )
idx_page_page_type_code ( page_type_code )
page_type_code
page_type_code varchar(20)
References page_type ( page_type_code -> code )
Unq unq_url_idx ( url )
url
url varchar(3000)
t
html_content
html_content text
t
http_status_code
http_status_code integer
#
accessed_time
accessed_time timestamp
d
site
Table crawldb.site
Unq unq_site_id ( id ) Pk pk_site_id ( id )
id
id * serial
Referred by page ( site_id -> id )
domain
domain varchar(500)
t
robots_content
robots_content text
t
sitemap_content
sitemap_content text
t
data_type
Table crawldb.data_type
Unq unq_data_type_code ( code )
code
code varchar(20)
Referred by page_data ( data_type_code -> code )
page_data
Table crawldb.page_data
id
id serial
#
idx_page_data_page_id ( page_id )
page_id
page_id integer
References page ( page_id -> id )
idx_page_data_data_type_code ( data_type_code )
data_type_code
data_type_code varchar(20)
References data_type ( data_type_code -> code )
data
data bytea
~
link
Table crawldb.link
Pk _0 ( from_page, to_page ) idx_link_from_page ( from_page )
from_page
from_page * integer
References page ( from_page -> id )
Pk _0 ( from_page, to_page ) idx_link_to_page ( to_page )
to_page
to_page * integer
References page ( to_page -> id )
page_type
Table crawldb.page_type
Unq unq_page_type_code ( code )
code
code varchar(20)
Referred by page ( page_type_code -> code )
image
Table crawldb.image
Pk pk_image_id ( id )
id
id * serial
#
idx_image_page_id ( page_id )
page_id
page_id integer
References page ( page_id -> id )
filename
filename varchar(255)
t
content_type
content_type varchar(50)
t
data
data bytea
~
accessed_time
accessed_time timestamp
d