Spaces:
Sleeping
Sleeping
Upload document_scrapped.py
Browse files- document_scrapped.py +161 -0
document_scrapped.py
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
+
"""document_scrapped.ipynb
|
3 |
+
|
4 |
+
Automatically generated by Colab.
|
5 |
+
|
6 |
+
Original file is located at
|
7 |
+
https://colab.research.google.com/drive/1cVGt7jq8uw5FYIwWOlUTAFbdVhPkU1FJ
|
8 |
+
"""
|
9 |
+
|
10 |
+
!pip install -r requirements.txt
|
11 |
+
|
12 |
+
!pip install python-docx
|
13 |
+
|
14 |
+
!pip install docx
|
15 |
+
|
16 |
+
!pip install PyMuPDF
|
17 |
+
|
18 |
+
!pip install python-pptx
|
19 |
+
|
20 |
+
from bs4 import BeautifulSoup
|
21 |
+
import requests
|
22 |
+
import json
|
23 |
+
import io
|
24 |
+
import fitz
|
25 |
+
from pptx import Presentation
|
26 |
+
import chardet
|
27 |
+
from docx import Document
|
28 |
+
import pandas as pd
|
29 |
+
|
30 |
+
|
31 |
+
def downl(url):
|
32 |
+
try:
|
33 |
+
rq = requests.get(url)
|
34 |
+
if rq.status_code != 200:
|
35 |
+
return None
|
36 |
+
bs = BeautifulSoup(rq.text, features='lxml')
|
37 |
+
lis = bs.find_all('ul', class_='dropdown-menu')[-1].find_all('li')
|
38 |
+
link = lis[-1].find('a').get('href')
|
39 |
+
return link
|
40 |
+
except Exception as e:
|
41 |
+
return None
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
def excel(link):
|
46 |
+
try:
|
47 |
+
ls = downl(link)
|
48 |
+
response = requests.get(ls)
|
49 |
+
|
50 |
+
if response.status_code == 200:
|
51 |
+
file_content = response.content
|
52 |
+
df = pd.read_excel(file_content)
|
53 |
+
if df.shape[0] > 50:
|
54 |
+
sample_size = 50
|
55 |
+
sample_df = df.sample(n=sample_size, random_state=42)
|
56 |
+
json_data = sample_df.to_json(orient='records')
|
57 |
+
js = json.loads(json_data)
|
58 |
+
return js
|
59 |
+
else:
|
60 |
+
print("Failed to download file")
|
61 |
+
except Exception as e:
|
62 |
+
return None
|
63 |
+
|
64 |
+
|
65 |
+
def csv(link):
|
66 |
+
try:
|
67 |
+
ls = downl(link)
|
68 |
+
print(ls)
|
69 |
+
response = requests.get(ls)
|
70 |
+
|
71 |
+
if response.status_code == 200:
|
72 |
+
file_content = response.content
|
73 |
+
detected_encoding = chardet.detect(file_content)['encoding']
|
74 |
+
df = pd.read_csv(io.BytesIO(file_content), encoding=detected_encoding, sep=';')
|
75 |
+
if df.empty:
|
76 |
+
print("The DataFrame is empty.")
|
77 |
+
return None
|
78 |
+
|
79 |
+
if df.shape[0] > 50:
|
80 |
+
sample_size = 50
|
81 |
+
sample_df = df.sample(n=sample_size, random_state=42)
|
82 |
+
else:
|
83 |
+
sample_df = df
|
84 |
+
|
85 |
+
json_data = sample_df.to_json(orient='records')
|
86 |
+
js = json.loads(json_data)
|
87 |
+
return js
|
88 |
+
|
89 |
+
except Exception as e:
|
90 |
+
return None
|
91 |
+
|
92 |
+
|
93 |
+
def docx(url):
|
94 |
+
try:
|
95 |
+
ls = downl(url)
|
96 |
+
# Download the .docx file
|
97 |
+
response = requests.get(ls)
|
98 |
+
response.raise_for_status() # Ensure we notice bad responses
|
99 |
+
|
100 |
+
# Read the .docx file
|
101 |
+
file_stream = io.BytesIO(response.content)
|
102 |
+
doc = Document(file_stream)
|
103 |
+
|
104 |
+
# Extract text
|
105 |
+
full_text = []
|
106 |
+
for para in doc.paragraphs:
|
107 |
+
full_text.append(para.text)
|
108 |
+
|
109 |
+
return '\n'.join(full_text)
|
110 |
+
except Exception as e:
|
111 |
+
print(f"An error occurred: {e}")
|
112 |
+
return None
|
113 |
+
|
114 |
+
|
115 |
+
def pdf(url):
|
116 |
+
try:
|
117 |
+
ls = downl(url)
|
118 |
+
# Download the PDF file
|
119 |
+
response = requests.get(ls)
|
120 |
+
response.raise_for_status() # Ensure we notice bad responses
|
121 |
+
|
122 |
+
# Read the PDF file
|
123 |
+
file_stream = io.BytesIO(response.content)
|
124 |
+
pdf_document = fitz.open(stream=file_stream, filetype='pdf')
|
125 |
+
|
126 |
+
# Extract text
|
127 |
+
full_text = []
|
128 |
+
for page_num in range(len(pdf_document)):
|
129 |
+
page = pdf_document.load_page(page_num)
|
130 |
+
full_text.append(page.get_text())
|
131 |
+
|
132 |
+
return '\n'.join(full_text)
|
133 |
+
except Exception as e:
|
134 |
+
print(f"An error occurred: {e}")
|
135 |
+
return None
|
136 |
+
|
137 |
+
|
138 |
+
|
139 |
+
|
140 |
+
def pptx(url):
|
141 |
+
try:
|
142 |
+
|
143 |
+
ls = downl(url)
|
144 |
+
response = requests.get(ls)
|
145 |
+
response.raise_for_status()
|
146 |
+
|
147 |
+
# Read the .pptx file
|
148 |
+
file_stream = io.BytesIO(response.content)
|
149 |
+
presentation = Presentation(file_stream)
|
150 |
+
|
151 |
+
# Extract text
|
152 |
+
full_text = []
|
153 |
+
for slide in presentation.slides:
|
154 |
+
for shape in slide.shapes:
|
155 |
+
if hasattr(shape, "text"):
|
156 |
+
full_text.append(shape.text)
|
157 |
+
|
158 |
+
return '\n'.join(full_text)
|
159 |
+
except Exception as e:
|
160 |
+
print(f"An error occurred: {e}")
|
161 |
+
return None
|