Spaces:
Sleeping
Sleeping
File size: 5,577 Bytes
b7d3039 3e4b286 b7d3039 3e4b286 b7d3039 3e4b286 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
import re
from bs4 import BeautifulSoup
import requests
import json
import io
import fitz
from pptx import Presentation
import chardet
from docx import Document
import pandas as pd
from io import BytesIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from io import StringIO
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from langchain.agents import (
create_react_agent,
AgentExecutor,
tool,
)
from langchain import hub
from langchain.tools.base import StructuredTool
from langchain.agents import initialize_agent
from langchain.prompts import StringPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from unidecode import unidecode
from langchain_huggingface import HuggingFaceEndpoint
import os
def select_words_until_char_limit(s, char_limit):
s_no_punct = re.sub(r'[^\w\s]', '', s) # remove punctuation, but leave spaces
words = s_no_punct.split()
selected_words = []
total_chars = 0
for word in words:
if total_chars + len(word) + 1 <= char_limit:
selected_words.append(word)
total_chars += len(word) + 1 # add 1 for the space
else:
break
return ' '.join(selected_words)
def downl(url):
try:
rq = requests.get(url)
if rq.status_code != 200:
return ""
bs = BeautifulSoup(rq.text, features='lxml')
lis = bs.find_all('ul', class_='dropdown-menu')[-1].find_all('li')
link = lis[-1].find('a').get('href')
print(link)
return link
except Exception as e:
return ""
def pdf(url):
# Download the PDF content
response = requests.get(url)
pdf_content = response.content
# Convert the bytes object to a file-like object
pdf_file = BytesIO(pdf_content)
# Extract text from the downloaded PDF content
resource_manager = PDFResourceManager()
fake_file_handle = StringIO()
converter = TextConverter(resource_manager, fake_file_handle, laparams=LAParams())
page_interpreter = PDFPageInterpreter(resource_manager, converter)
for page in PDFPage.get_pages(pdf_file):
page_interpreter.process_page(page)
text = fake_file_handle.getvalue()
f = select_words_until_char_limit(text, 30000)
converter.close()
fake_file_handle.close()
return f
def excel(link : str) -> str:
try:
response = requests.get(link)
if response.status_code == 200:
file_content = response.content
df = pd.read_excel(file_content)
if df.shape[0] > 50:
sample_size = 50
sample_df = df.sample(n=sample_size, random_state=42)
else:
sample_df = df
json_data = sample_df.to_json(orient='records')
js = json.loads(json_data)
return f"{js}"
else:
print("Failed to download file")
return "No dat avaible error"
except Exception as e:
print(e)
return "No data avaible"
def csv(link : str) -> str:
try:
response = requests.get(link)
if response.status_code == 200:
file_content = response.content
detected_encoding = chardet.detect(file_content)['encoding']
df = pd.read_csv(io.BytesIO(file_content), encoding=detected_encoding, sep=';')
if df.empty:
print("The DataFrame is empty.")
return 'The data frame is empty'
if df.shape[0] > 50:
sample_size = 50
sample_df = df.sample(n=sample_size, random_state=42)
else:
sample_df = df
json_data = sample_df.to_json(orient='records')
js = json.loads(json_data)
return f"{js}"
except Exception as e:
return 'No data avaible'
def docx(url : str) -> str:
try:
response = requests.get(url)
response.raise_for_status() # Ensure we notice bad responses
# Read the .docx file
file_stream = io.BytesIO(response.content)
doc = Document(file_stream)
# Extract text
full_text = []
for para in doc.paragraphs:
full_text.append(para.text)
f = "\n".join(full_text)
n = select_words_until_char_limit(f, 30000)
return n
except Exception as e:
print(f"An error occurred: {e}")
return 'No data avaible'
def pptx(url : str) -> str:
try:
response = requests.get(url)
response.raise_for_status()
# Read the .pptx file
file_stream = io.BytesIO(response.content)
presentation = Presentation(file_stream)
# Extract text
full_text = []
for slide in presentation.slides:
for shape in slide.shapes:
if hasattr(shape, "text"):
full_text.append(shape.text)
g = "\n".join(full_text)
c = select_words_until_char_limit(g, 30000)
return c
except Exception as e:
print(f"An error occurred: {e}")
return 'No data avaible'
def get_data(url):
ki = url.replace('\nObservation', '').replace('"\nObservation', '')
jo = downl(ki)
ext = jo.split(".")[-1]
if ext == 'xlsx' or ext == 'xls' or ext == 'xlsm':
rs = excel(jo)
return rs
elif ext == 'pdf':
rs = pdf(jo)
return rs
elif ext == 'docx' or ext == 'doc':
rs = docx(jo)
return rs
elif ext == 'csv':
rs = csv(jo)
return rs
elif ext == 'pptx' or ext == 'ppt':
rs = pptx(jo)
return rs
return "No data returned"
|