🚧 Colour based tagging & non-ocr page_to_text

pyproject.toml

@@ -14,6 +14,8 @@ playwright = "^1.44.0"
 selenium = "^4.21.0"
 google-cloud-vision = "^3.7.2"
 azure-ai-vision-imageanalysis = "^1.0.0b2"
+pillow = "^10.4.0"
+numpy = "^2.0.1"
 
 
 [tool.poetry.group.dev.dependencies]

scripts/setup.sh

@@ -5,4 +5,8 @@ cd ..
 npm install
 npm run build
 
-poetry install
+poetry install
+
+cd ./tarsier-snapshots || exit 1
+poetry install
+poetry run bananalyze --download

tarsier-snapshots/snapshots/0fdyKSMbc3kVUgL9RGiEk/ocr.txt

@@ -1,64 +1,61 @@
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
-[ 0 ] O'MELVENY WORLDWIDE
-            [ @ 1 ]
-              **' Melveny**         [ 2 ] PROFESSIONALS [ 3 ] SERVICES [ 4 ] INSIGHTS [ 5 ] NEWS [ 6 ] LOCATIONS       [ 7 ] ABOUT [ @ 8 ] CAREERS [ @ 9 ] ALUMNI  ☐
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+[0] O Melveny Worldwide
+                                   [2] Professionals       [3] Services     [4] Insights     [5] News     [6] Locations                     [7] About      [@8] Careers [@9] Alumni
 
-         [ @ 10 ] Our Team > [ 11 ] Ryan Coombs
-                                                                                                               [ 20 ] AREAS OF FOCUS
-                                                                                                               [ @ 21 ] Bank Finance
-                                                                                                               [ @ 22 ] Capital Markets
-                                                                                                               [ @ 23 ] Emerging Companies
-                                                                                                               [ @ 24 ] Private Equity
-                                                                                                               [ @ 25 ] Public Company Advisory
+  [@10] Our Team [11] Ryan Coombs
+                                                                                                                                  [20] Areas of Focus
 
+                                                                                                                                 [@21] Bank Finance
+                                                                                                                                 [@22] Capital Markets
+                                                                                                                                 [@23] Emerging Companies
+                                                                                                                                 [@24] Private Equity
+                                                                                                                                 [@25] Public Company Advisory
 
 
 
 
 
 
+                                                                                                                        [37] O Melveny uses cookies to improve website functionality
+                                                                                                                        and performance. By continuing to this website, you are
+                                                                                                                        agreeing to our Cookie Policy.
+                                                                                                                             [$39] Only use essential cookies    [$40] Accept Cookies
 
 
+      **[12] Ryan Coombs**                                                                           [@14] San Francisco Office
+      [13] Partner
 
+      [@15] rcoombs omm.com     [16] D: +1-415-984-8943
 
+     [@26] Overview [@27] News [@28] Credentials
 
-             [ 12 ] Ryan Coombs                                                      [ @ 14 ] San Francisco Office
-            [ 13 ] Partner
+  **[29] Ryan Coombs structures and executes a broad range of capital**
+  **markets transactions for issuers and investment banks, including initial**
+  **public offerings and other common and preferred equity offerings,**
+  **investment grade and high-yield debt issuances, convertible notes**
+  **offerings, SPAC transactions, PIPEs, and other complex capital-raising**
+  **transactions. Clients turn to Ryan for counsel on public company**
+  **reporting, corporate governance and other corporate matters.**
+  [30] Ryan s experience spans a variety of sectors, with an emphasis on technology, and includes social media,
+  consumer electronics, and software, as well as entertainment, life sciences, healthcare and renewable energy.
 
-            [ @ 15 ] [email protected] [ 16 ] D: [ @ 17 ] + 1-415-984-8943            [ @ 18 ]   [ @ 19 ]
 
-           [ @ 26 ] OVERVIEW [ @ 27 ] NEWS [ @ 28 ] CREDENTIALS
+  [31] Related Practices
 
+  [@32] Bank Finance
 
-         **[ 29 ] Ryan Coombs structures and executes a broad range of capital**
-         markets transactions for issuers and investment banks, including initial
-         public offerings and other common and preferred equity offerings,
-         investment grade and high - yield debt issuances, convertible notes
-         offerings, SPAC transactions, PIPES, and other complex capital - raising
-         **transactions. Clients turn to Ryan for counsel on public company**
-         **reporting, corporate governance and other corporate matters.**
-         [ 30 ] Ryan's experience spans a variety of sectors, with an emphasis on technology, and includes social media, consumer
-         electronics, and software, as well as entertainment, life sciences, healthcare and renewable energy.
+  [@33] Capital Markets
 
+  [@34] Emerging Companies
 
-           [ 31 ] RELATED PRACTICES
-           [ @ 32 ] Bank Finance
+  [@35] Private Equity
 
-           [ @ 33 ] Capital Markets
+  [@36] Public Company Advisory
 
-           [ @ 34 ] Emerging Companies
 
-           [ @ 35 ] Private Equity
 
-           [ @ 36 ] Public Company Advisory.
 
-
-                                                                                                                [ 37 ] O'Melveny uses cookies to improve website functionality
-                                                                                                               and performance. By continuing to this website, you are
-                                                                                                               agreeing to our [ @ 39 ] Cookie Policy [ 38 ].
-           [ @ 42 ]
-                                      [ 48 ] O'Melveny's latest insights, straight to your inbox [ @ 49 ] Subscribe [ @ 43 ] [ @ 44 ] Only [ @ 45 ] tial Co [ @ 46 ] [ @ 47 ] .ccept Cookies
-           O'Melveny
-           [ @ 51 ] DISCLAIMER [ @ 52 ] PRIVACY POLICY [ @ 53 ] CONTACT US                      [ 50 ] ATTORNEY ADVERTISING © 2023 O'MELVENY & MYERS LLP. ALL RIGHTS RESERVED
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
-Token count: 638
+                                                                                          [47] O Melveny s latest insights, straight to your inbox [@48] Subscribe
+  [@50] Disclaimer [@51] Privacy Policy [@52] Contact Us                                                        [49] Attorney Advertising 2023 O'Melveny & Myers LLP. All rights reserved
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+Token count: 483