Not all rows have been extracted (scraped) - Element wrong setting

Hello @ll, I am extracting data from tables on page Seznam kulturních památek v okrese Zlín – Wikipedie , but unfortunately only the first row of the table is extracted each time and I am unable to extrat all rows of the table.
I probably have the Element set wrong, but I don't know how to set it exactly - table:nth-of-type(n+3) > tbody

Url: Seznam kulturních památek v okrese Zlín – Wikipedie

Sitemap:
{"_id":"SEZNAM__nemovitych_kulturnich_pamatek_v_cr_LIST","startUrl":["https://cs.wikipedia.org/wiki/Seznam_kulturn%C3%ADch_pam%C3%A1tek_v_okrese_Zl%C3%ADn"],"selectors":[{"id":"ELEMENT LIST","multiple":true,"parentSelectors":["_root"],"selector":"table:nth-of-type(n+3) > tbody","type":"SelectorElement"},{"id":"IMG list","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"img","type":"SelectorImage"},{"id":"GEO list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"tr.vcard:nth-of-type(1) > td:nth-of-type(5)","type":"SelectorHTML"},{"id":"NAME list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"tr.vcard:nth-of-type(1)","type":"SelectorHTML"},{"id":"OBEC list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"tr.vcard:nth-of-type(1) > td:nth-of-type(4)","type":"SelectorText"},{"id":"LINK AUTOR list","linkType":"linkFromHref","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"a.mw-file-description","type":"SelectorLink"},{"id":"LINK IN","linkType":"linkFromHref","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"a.extiw","type":"SelectorLink"},{"id":"KATEGORIE","multiple":false,"parentSelectors":["LINK IN"],"regex":"","selector":"div.wikibase-snakview-body","type":"SelectorText"},{"id":"LINK IN IMG","linkType":"linkFromHref","multiple":false,"parentSelectors":["LINK IN"],"selector":".commons-media-caption a","type":"SelectorLink"},{"id":"LINK IMG DETAIL","linkType":"linkFromHref","multiple":false,"parentSelectors":["LINK IN IMG"],"selector":".mw-gu-onwiki-cs_wikipedia_org li:nth-of-type(3) a","type":"SelectorLink"},{"id":"POPIS","multiple":false,"parentSelectors":["LINK IMG DETAIL"],"regex":"","selector":"p","type":"SelectorHTML"}]}

Thank you for your help

try this, but keep going

{"_id":"SEZNAM__nemovitych_kulturnich_pamatek_v_cr_LIST","startUrl":["https://cs.wikipedia.org/wiki/Seznam_kulturn%C3%ADch_pam%C3%A1tek_v_okrese_Zl%C3%ADn"],"selectors":[{"id":"ELEMENT LIST","multiple":true,"parentSelectors":["_root"],"selector":"tr.vcard","type":"SelectorElement"},{"extractAttribute":"href","id":"IMG list","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"a.mw-file-description","type":"SelectorElementAttribute"},{"id":"GEO list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"span.coordinates","type":"SelectorText"},{"id":"NAME list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"td:has(a.extiw)","type":"SelectorHTML"},{"id":"OBEC list","multiple":false,"parentSelectors":["ELEMENT LIST"],"regex":"","selector":"tr.vcard:nth-of-type(1) > td:nth-of-type(4)","type":"SelectorText"},{"id":"LINK AUTOR list","linkType":"linkFromHref","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"a.mw-file-description","type":"SelectorLink"},{"id":"LINK IN","linkType":"linkFromHref","multiple":false,"parentSelectors":["ELEMENT LIST"],"selector":"a.extiw","type":"SelectorLink"},{"id":"KATEGORIE","multiple":false,"parentSelectors":["LINK IN"],"regex":"","selector":"div.wikibase-snakview-body","type":"SelectorText"},{"id":"LINK IN IMG","linkType":"linkFromHref","multiple":false,"parentSelectors":["LINK IN"],"selector":".commons-media-caption a","type":"SelectorLink"},{"id":"LINK IMG DETAIL","linkType":"linkFromHref","multiple":false,"parentSelectors":["LINK IN IMG"],"selector":".mw-gu-onwiki-cs_wikipedia_org li:nth-of-type(3) a","type":"SelectorLink"},{"id":"POPIS","multiple":false,"parentSelectors":["LINK IMG DETAIL"],"regex":"","selector":"p","type":"SelectorHTML"}]}

Thank you.
And do you know why there are 185 marked and only 163 extracted?

Now it extracted 180 :slight_smile:

Hi,

Can you please explain what is the purpose of the 'LINK IN' selector?

I don't even know anymore, I redid the whole thing :smiley:

1 Like