main

code/main_extractor.py

@@ -8,6 +8,8 @@ Created on Fri Dec 13 10:48:25 2019
 import json
 from bs4 import BeautifulSoup
 import requests
+import tika
+tika.initVM()
 from tika import parser as pdf_parser
 import re
 import html_extractor
@@ -219,7 +221,12 @@ def iterate(data):
     de_en = open_json(DE_EN)
     for i, el in enumerate(data.items()):
         if el[0] in de_en:
+            print(el[0], ' there')
             continue
+        #elif el[0] == '1613752':
+            #print('passed 1613752')
+            #continue
+        print(el[0])
         extracted = extractor(el)
         if extracted == False:
             with open(FAILS,'r') as f: