File size: 4,157 Bytes
c4331f2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
from datetime import date, timedelta

import bs4
from langchain.indexes import SQLRecordManager, index
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores.chroma import Chroma
from langchain_community.document_loaders import WebBaseLoader
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait

import config

DATA_URL = "https://www.sikafinance.com/marches/actualites_bourse_brvm"

embeddings_model = GoogleGenerativeAIEmbeddings(
    model=config.GOOGLE_EMBEDDING_MODEL
)  # type: ignore


options = webdriver.ChromeOptions()
options.add_argument("--headless")
options.add_argument("--no-sandbox")
options.add_argument("--disable-dev-shm-usage")
driver = webdriver.Chrome(options=options)


def scrap_articles(
    url="https://www.sikafinance.com/marches/actualites_bourse_brvm", num_days_past=5
):

    today = date.today()

    driver.get(url)

    all_articles = []
    for i in range(num_days_past + 1):
        past_date = today - timedelta(days=i)
        date_str = past_date.strftime("%Y-%m-%d")
        WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "dateActu"))
        )
        text_box = driver.find_element(By.ID, "dateActu")
        text_box.send_keys(date_str)

        submit_btn = WebDriverWait(driver, 10).until(
            EC.element_to_be_clickable((By.ID, "btn"))
        )
        submit_btn.click()

        dates = driver.find_elements(By.CLASS_NAME, "sp1")
        titles = driver.find_elements(By.XPATH, "//td/a")

        articles = []
        for i in range(len(titles)):
            art = {
                "title": titles[i].text.strip(),
                "date": dates[i].text,
                "link": titles[i].get_attribute("href"),
            }
            articles.append(art)

        all_articles += articles
    # driver.quit()

    return all_articles


def set_metadata(documents, metadatas):
    """
    #Edit a metadata of lanchain Documents object
    """
    for doc in documents:
        idx = documents.index(doc)
        doc.metadata = metadatas[idx]
    print("Metadata successfully changed")
    print(documents[0].metadata)


def process_docs(
    articles, persist_directory, embeddings_model, chunk_size=1000, chunk_overlap=100
):
    """
    #Scrap all articles urls content and save on a vector DB
    """
    article_urls = [a["link"] for a in articles]

    print("Starting to scrap ..")

    loader = WebBaseLoader(
        web_paths=article_urls,
        bs_kwargs=dict(
            parse_only=bs4.SoupStrainer(
                class_=("inarticle txtbig", "dt_sign", "innerUp")
            )
        ),
    )

    print("After scraping Loading ..")
    docs = loader.load()

    # Update metadata: add title,
    set_metadata(documents=docs, metadatas=articles)

    print("Successfully loaded to document")

    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size, chunk_overlap=chunk_overlap, separators=["\n"]
    )
    splits = text_splitter.split_documents(docs)

    # Create the storage path if it doesn't exist
    if not os.path.exists(persist_directory):
        os.makedirs(persist_directory)

    doc_search = Chroma.from_documents(
        documents=splits,
        embedding=embeddings_model,
        persist_directory=persist_directory,
    )

    # Indexing data
    namespace = "chromadb/my_documents"
    record_manager = SQLRecordManager(
        namespace, db_url="sqlite:///record_manager_cache.sql"
    )
    record_manager.create_schema()

    index_result = index(
        docs,
        record_manager,
        doc_search,
        cleanup="incremental",
        source_id_key="link",
    )

    print(f"Indexing stats: {index_result}")

    return doc_search


if __name__ == "__main__":

    data = scrap_articles(DATA_URL, num_days_past=2)
    vectordb = process_docs(data, config.STORAGE_PATH, embeddings_model)
    ret = vectordb.as_retriever()