Spaces:
Running
Running
Commit
·
a4aec71
1
Parent(s):
3dd67db
Create textractor.py
Browse files- textractor.py +25 -0
textractor.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Textractor module
|
| 3 |
+
"""
|
| 4 |
+
|
| 5 |
+
import requests
|
| 6 |
+
|
| 7 |
+
from bs4 import BeautifulSoup
|
| 8 |
+
|
| 9 |
+
from txtai.pipeline.segmentation import Segmentation
|
| 10 |
+
|
| 11 |
+
class Textractor(Segmentation):
|
| 12 |
+
"""
|
| 13 |
+
Extracts text from files.
|
| 14 |
+
"""
|
| 15 |
+
|
| 16 |
+
def __init__(self, sentences=False, lines=False, paragraphs=False, minlength=None, join=False):
|
| 17 |
+
super().__init__(sentences, lines, paragraphs, minlength, join)
|
| 18 |
+
|
| 19 |
+
def text(self, text):
|
| 20 |
+
# text is a url
|
| 21 |
+
response = requests.get(text)
|
| 22 |
+
html = response.text
|
| 23 |
+
|
| 24 |
+
soup = BeautifulSoup(html, features="html.parser")
|
| 25 |
+
return soup.get_text()
|