From bb5f8a9fe7f3968588b45eeaa0c993ef314ca904 Mon Sep 17 00:00:00 2001
From: Jules Laplace <julescarbon@gmail.com>
Date: Wed, 1 Apr 2020 01:05:53 +0200
Subject: begin bridge

---
 cli/app/thesaurus/api.py | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

(limited to 'cli/app/thesaurus/api.py')

diff --git a/cli/app/thesaurus/api.py b/cli/app/thesaurus/api.py
index ad0dd92..98e0210 100644
--- a/cli/app/thesaurus/api.py
+++ b/cli/app/thesaurus/api.py
@@ -1,5 +1,6 @@
 import os
 import requests
+from hashlib import sha256
 
 from app.utils.util import *
 from app.settings import app_cfg
@@ -40,9 +41,23 @@ class ThesaurusAPI:
     if resp.status_code != 200:
       return []
     data = resp.text
-    data = data.split('<div id="resultsTimelineData">')
-    data = data[0].split('</div>')
-    return json.loads(data)
+    data = data.split('<div id="resultsTimelineData">')[1].split('</div>')[0]
+    # print(data)
+    rows = json.loads(data)
+    cats = []
+    for row in rows:
+      cat, years = row['popup'].split(']: ')
+      cat = cat.split('[')[1]
+      cats.append({
+        'catid': row['catid'],
+        'catnum': row['catnum'],
+        'category': cat,
+        'years': years,
+      })
+    return {
+      'word': word,
+      'categories': cats,
+    }
 
   def category(self, id):
     query = {
@@ -52,20 +67,20 @@ class ThesaurusAPI:
     if resp.status_code != 200:
       return ""
     raw = resp.text
-    classification = raw.split("<span style='font-size: 0.6em'>")[1].split('</span>')[0]
-    category = raw.split("<br />")[1].split('</h2>')[0]
-    raw_words = raw.split('<b>')[1:]
+    catnum = raw.split("<span style='font-size: 0.6em'>")[1].split('</span>')[0]
+    category = raw.split("<br />")[1].split('</h2>')[0].replace("<span style='font-size: 0.6em'>", "").replace("</span>", "")
+    raw_words = raw.split('"><b>')[1:]
     words = []
     for word in raw_words:
       word, rest = word.split('</b>')
-      years = word.split(' <span')[0].trim()
+      years = word.split(' <span')[0].strip()
       words.append({
         'word': word,
         'years': years,
       })
     return {
-      'id': id,
+      'catid': id,
+      'catnum': catnum,
       'category': category,
-      'classification': classification,
       'words': words,
     }
\ No newline at end of file
-- 
cgit v1.2.3-70-g09d2