pt/scrape
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Paul Trowbridge 2019-12-13 17:32:48 -05:00
commit 0563409a98
2 changed files with 1147 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
extract_images.sql Normal file
View File

@ -0,0 +1,11 @@
SELECT
raw.code
--,raw.url
,x.seq
,mold.code[1]
,mold.seq
,x.img[1] img
FROM
scrape.raw
LEFT JOIN LATERAL REGEXP_MATCHES(html, $$background-image: url\((.*?(.jpg))$$::TEXT,'g') WITH ORDINALITY AS x(img, seq) ON TRUE
LEFT JOIN LATERAL regexp_matches(x.img[1],$$([A-Z,\.,0-9]{7,8}).*\.jpg$$) WITH ORDINALITY AS mold(code, seq) ON TRUE

1136
greenhouse_decorative.html Normal file
View File

File diff suppressed because it is too large Load Diff