chaindl 0.1.0__tar.gz

chaindl-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Dhruvan Gnanadhandayuthapani
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

chaindl-0.1.0/PKG-INFO

@@ -0,0 +1,85 @@
+Metadata-Version: 2.4
+Name: chaindl
+Version: 0.1.0
+Summary: Download crypto on-chain data with a single line of code 
+Author-email: Dhruvan Gnanadhandayuthapani <dhruvan2006@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/dhruvan2006/chaindl
+Project-URL: Documentation, https://chaindl.readthedocs.io/
+Project-URL: PyPI, https://pypi.org/project/chaindl/
+Project-URL: Issues, https://github.com/dhruvan2006/chaindl/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: pandas
+Requires-Dist: beautifulsoup4
+Requires-Dist: seleniumbase
+Requires-Dist: selenium
+Requires-Dist: selenium-wire
+Requires-Dist: blinker==1.7.0
+Dynamic: license-file
+
+# chaindl
+
+**Download crypto on-chain data with a single line of code.**
+
+[![Build Passing](https://github.com/dhruvan2006/chaindl/actions/workflows/release.yml/badge.svg)](https://github.com/dhruvan2006/chaindl/actions/workflows/release.yml)
+[![Tests Passing](https://github.com/dhruvan2006/chaindl/actions/workflows/tests.yml/badge.svg)](https://github.com/dhruvan2006/chaindl/actions/workflows/tests.yml)
+[![PyPI - Version](https://img.shields.io/pypi/v/chaindl)](https://pypi.org/project/chaindl/)
+[![PyPI Downloads](https://static.pepy.tech/badge/ocfinance)](https://pypi.org/project/chaindl/)
+[![GitHub License](https://img.shields.io/github/license/dhruvan2006/chaindl)](https://github.com/dhruvan2006/chaindl)
+
+`chaindl` is a lightweight Python library that lets you fetch historical and live on-chain crypto data from multiple 
+public sources in one step. Whether you want to analyze metrics from Bitcoin, Ethereum, or other chains, `chaindl` 
+handles the heavy lifting so you can focus on insights.
+
+## Why Use `chaindl`?
+
+- **Fetch crypto on-chain data in one line** – no need for API keys or complicated setups.  
+- **Fully free** – all functionality is available without subscription or payment.  
+- **Ready for analysis** – data comes back as a `pandas.DataFrame`, so you can immediately manipulate, visualize, or model it.  
+- **Save and share** – easily export data as CSV for offline use, Excel, or reporting.  
+- **Multiple sources supported** – from Cryptoquant to CheckOnChain, get all your metrics without juggling different platforms.  
+- **Focus on insights, not boilerplate** – `chaindl` handles parsing and formatting, so you spend less time on setup.
+
+## Documentation: [https://chaindl.readthedocs.io/](https://chaindl.readthedocs.io/)
+
+**Complete documentation is available at:** 
+[https://chaindl.readthedocs.io/](https://chaindl.readthedocs.io/)
+
+## Supported Websites
+- [CheckOnChain](https://charts.checkonchain.com/)
+- [ChainExposed](https://chainexposed.com/)
+- [Woocharts](https://woocharts.com/)
+- [Cryptoquant](https://cryptoquant.com/)
+- [Bitbo Charts](https://charts.bitbo.io/)
+- [Bitcoin Magazine Pro](https://www.bitcoinmagazinepro.com)
+- [Blockchain.com](https://www.blockchain.com/explorer/charts)
+
+## Installation
+To install the `chaindl` package, use pip:
+```bash
+pip install chaindl
+```
+
+## Quick Start
+To download the data of a chart, simply obtain the URL and pass it to the download function
+
+```python
+import chaindl
+
+# Download data from a URL
+data = chaindl.download("https://charts.checkonchain.com/btconchain/pricing/pricing_picycleindicator/pricing_picycleindicator_light.html")
+
+# Export to CSV
+data.to_csv('out.csv')
+
+# Quick Plot
+data.plot()
+```
+
+For advanced usage and examples with Cryptoquant and other sources, see the [documentation](https://chaindl.readthedocs.io/).

chaindl-0.1.0/README.md

@@ -0,0 +1,60 @@
+# chaindl
+
+**Download crypto on-chain data with a single line of code.**
+
+[![Build Passing](https://github.com/dhruvan2006/chaindl/actions/workflows/release.yml/badge.svg)](https://github.com/dhruvan2006/chaindl/actions/workflows/release.yml)
+[![Tests Passing](https://github.com/dhruvan2006/chaindl/actions/workflows/tests.yml/badge.svg)](https://github.com/dhruvan2006/chaindl/actions/workflows/tests.yml)
+[![PyPI - Version](https://img.shields.io/pypi/v/chaindl)](https://pypi.org/project/chaindl/)
+[![PyPI Downloads](https://static.pepy.tech/badge/ocfinance)](https://pypi.org/project/chaindl/)
+[![GitHub License](https://img.shields.io/github/license/dhruvan2006/chaindl)](https://github.com/dhruvan2006/chaindl)
+
+`chaindl` is a lightweight Python library that lets you fetch historical and live on-chain crypto data from multiple 
+public sources in one step. Whether you want to analyze metrics from Bitcoin, Ethereum, or other chains, `chaindl` 
+handles the heavy lifting so you can focus on insights.
+
+## Why Use `chaindl`?
+
+- **Fetch crypto on-chain data in one line** – no need for API keys or complicated setups.  
+- **Fully free** – all functionality is available without subscription or payment.  
+- **Ready for analysis** – data comes back as a `pandas.DataFrame`, so you can immediately manipulate, visualize, or model it.  
+- **Save and share** – easily export data as CSV for offline use, Excel, or reporting.  
+- **Multiple sources supported** – from Cryptoquant to CheckOnChain, get all your metrics without juggling different platforms.  
+- **Focus on insights, not boilerplate** – `chaindl` handles parsing and formatting, so you spend less time on setup.
+
+## Documentation: [https://chaindl.readthedocs.io/](https://chaindl.readthedocs.io/)
+
+**Complete documentation is available at:** 
+[https://chaindl.readthedocs.io/](https://chaindl.readthedocs.io/)
+
+## Supported Websites
+- [CheckOnChain](https://charts.checkonchain.com/)
+- [ChainExposed](https://chainexposed.com/)
+- [Woocharts](https://woocharts.com/)
+- [Cryptoquant](https://cryptoquant.com/)
+- [Bitbo Charts](https://charts.bitbo.io/)
+- [Bitcoin Magazine Pro](https://www.bitcoinmagazinepro.com)
+- [Blockchain.com](https://www.blockchain.com/explorer/charts)
+
+## Installation
+To install the `chaindl` package, use pip:
+```bash
+pip install chaindl
+```
+
+## Quick Start
+To download the data of a chart, simply obtain the URL and pass it to the download function
+
+```python
+import chaindl
+
+# Download data from a URL
+data = chaindl.download("https://charts.checkonchain.com/btconchain/pricing/pricing_picycleindicator/pricing_picycleindicator_light.html")
+
+# Export to CSV
+data.to_csv('out.csv')
+
+# Quick Plot
+data.plot()
+```
+
+For advanced usage and examples with Cryptoquant and other sources, see the [documentation](https://chaindl.readthedocs.io/).

chaindl-0.1.0/chaindl/__init__.py

@@ -0,0 +1 @@
+from .download import download

chaindl-0.1.0/chaindl/download.py

@@ -0,0 +1,72 @@
+import pandas as pd
+
+from . import scraper
+
+def download(url, start=None, end=None, **kwargs):
+    """
+    Downloads cryptocurrency data from the specified URL and returns it as a pandas DataFrame.
+
+    This function supports various data sources and handles specific URLs to retrieve data from each.
+
+    Args:
+        url (str): The URL from which to download the data. It must match one of the known data sources.
+        start (str, optional): The start date for slicing the DataFrame. Must be in a format recognized by pandas (e.g., 'YYYY-MM-DD').
+        end (str, optional): The end date for slicing the DataFrame. Must be in a format recognized by pandas (e.g., 'YYYY-MM-DD').
+        **kwargs: Additional keyword arguments to pass to specific scraper methods.\n
+            email and password needs to be passed for Cryptoquant\n
+            sbr_webdriver needs to be passed for using a remote browser proxy (Eg: BrightData, etc.)
+
+    Returns:
+        pd.DataFrame: A DataFrame containing the downloaded data. The DataFrame index is datetime.
+
+    Raises:
+        ValueError: If the provided URL does not match any known data sources.
+
+    Supported Data Sources:
+        - CheckOnChain: "https://charts.checkonchain.com"
+        - ChainExposed: "https://chainexposed.com"
+        - BitBo: "https://charts.bitbo.io"
+        - WooCharts: "https://woocharts.com"
+        - CryptoQuant: "https://cryptoquant.com"
+        - Bitcoin Magazine Pro: "https://www.bitcoinmagazinepro.com"
+        - Blockchain.com: "https://www.blockchain.com/explorer/charts"
+
+    Example:
+        >>> df = download("https://charts.checkonchain.com/path/to/indicator")
+        >>> df_filtered = download("https://charts.checkonchain.com/path/to/indicator", start='2023-01-01', end='2023-12-31')
+        >>> cryptoquant = download("https://cryptoquant.com/path/to/indicator", email=email, password=password)
+    """
+    CHECKONCHAIN_BASE_URL = "https://charts.checkonchain.com"
+    CHAINEXPOSED_BASE_URL = "https://chainexposed.com"
+    BITBO_BASE_URL = "https://charts.bitbo.io"
+    WOOCHARTS_BASE_URL = "https://woocharts.com"
+    CRYPTOQUANT_BASE_URL = "https://cryptoquant.com"
+    BITCOINMAGAZINEPRO_BASE_URL = "https://www.bitcoinmagazinepro.com"
+    BLOCKCHAIN_BASE_URL = "https://www.blockchain.com/explorer/charts"
+
+    data = pd.DataFrame()
+
+    if url.startswith(CHECKONCHAIN_BASE_URL):
+        data = scraper.checkonchain._download(url)
+    elif url.startswith(CHAINEXPOSED_BASE_URL):
+        data = scraper.chainexposed._download(url)
+    elif url.startswith(BITBO_BASE_URL):
+        data = scraper.bitbo._download(url, **kwargs)
+    elif url.startswith(WOOCHARTS_BASE_URL):
+        data = scraper.woocharts._download(url)
+    elif url.startswith(CRYPTOQUANT_BASE_URL):
+        data = scraper.cryptoquant._download(url, **kwargs)
+    elif url.startswith(BITCOINMAGAZINEPRO_BASE_URL):
+        data = scraper.bitcoinmagazinepro._download(url, **kwargs)
+    elif url.startswith(BLOCKCHAIN_BASE_URL):
+        data = scraper.blockchain._download(url, **kwargs)
+    else:
+        raise ValueError("Unsupported source. Find the list of supported websites here: https://chaindl.readthedocs.io/")
+    
+    if pd.api.types.is_datetime64_any_dtype(data.index):
+        if start:
+            data = data.loc[start:]
+        if end:
+            data = data.loc[:end]
+
+    return data

chaindl-0.1.0/chaindl/scraper/__init__.py

@@ -0,0 +1,7 @@
+from .checkonchain import _download
+from .chainexposed import _download
+from .bitbo import _download
+from .woocharts import _download
+from .cryptoquant import _download
+from .bitcoinmagazinepro import _download
+from .blockchain import _download

chaindl-0.1.0/chaindl/scraper/bitbo.py

@@ -0,0 +1,117 @@
+import re
+import json
+import time
+import pandas as pd
+
+from selenium.webdriver import Remote, ChromeOptions
+from selenium.webdriver.chromium.remote_connection import ChromiumRemoteConnection
+from selenium.webdriver.common.by import By
+
+from seleniumbase import SB
+from selenium.common.exceptions import StaleElementReferenceException
+
+def _download(url, **kwargs):
+    content = _get_script_content(url, **kwargs)
+    traces = _get_traces(content)
+
+    dfs = []
+    for trace in traces:
+        name, x, y = _get_data(trace, content)
+
+        df = pd.DataFrame({ name: pd.to_numeric(y, errors='coerce') }, index=pd.to_datetime(x))
+        df.index.name = 'Date'
+        dfs.append(df)
+
+    merged_df = pd.concat(dfs, axis=1, join='outer')
+    return merged_df
+
+def _get_script_content(url, **kwargs):
+    sbr_webdriver = kwargs.get('sbr_webdriver')
+    if sbr_webdriver:
+        return _get_script_content_brightdata(url, sbr_webdriver)
+    else:
+        return _get_script_content_seleniumbase(url)
+
+def _get_script_content_brightdata(url, sbr_webdriver):
+    sbr_connection = ChromiumRemoteConnection(sbr_webdriver, 'goog', 'chrome')
+    with Remote(sbr_connection, options=ChromeOptions()) as driver:
+        driver.get(url)
+
+        # CAPTCHA handling: If you're expecting a CAPTCHA on the target page, use the following code snippet to check the status of Scraping Browser's automatic CAPTCHA solver
+        print('Waiting captcha to solve...')
+        solve_res = driver.execute('executeCdpCommand', {
+            'cmd': 'Captcha.waitForSolve',
+            'params': {'detectTimeout': 20000},
+        })
+        print('Captcha solve status:', solve_res['value']['status'])
+
+        script_content = ""
+        script_tags = driver.find_elements(By.TAG_NAME, 'script')
+        for script_tag in script_tags:
+            script_inner_html = script_tag.get_attribute("innerHTML")
+            if script_inner_html and 'trace' in script_inner_html:
+                script_content += script_inner_html
+    
+    return script_content
+
+def _get_script_content_seleniumbase(url):
+    script_content = ""
+    with SB(uc=True) as sb:
+        sb.uc_open_with_reconnect(url, 4)
+        sb.uc_gui_click_captcha()
+
+        attempts = 0
+        while attempts < 3:
+            try:
+                script_tags = sb.find_elements("script")
+                for script_tag in script_tags:
+                    script_inner_html = script_tag.get_attribute("innerHTML")
+                    if script_inner_html and 'trace' in script_inner_html:
+                        script_content += script_inner_html
+                break
+            except StaleElementReferenceException:
+                attempts += 1
+                time.sleep(1)
+
+    return script_content
+
+def _get_traces(content):
+    trace_pattern = r'var\s+trace\d+\s*=\s*(\{.*?\});'
+    traces = re.findall(trace_pattern, content, re.DOTALL)
+    return traces
+
+def _get_data(trace, content):
+    x_pattern = r'x:\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*,'
+    y_pattern = r'y:\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*,'
+    name_pattern = r"name:\s*'([^']*)'"
+    var_pattern = r'var\s+({name})\s*=\s*([^;]*);'
+
+    name = ""
+    x, y = [], []
+
+    x_match = re.search(x_pattern, trace)
+    y_match = re.search(y_pattern, trace)
+
+    if x_match and y_match:
+        x_var_name = x_match.group(1)
+        y_var_name = y_match.group(1)
+
+        x_var_pattern = var_pattern.format(name=x_var_name)
+        y_var_pattern = var_pattern.format(name=y_var_name)
+
+        x = re.search(x_var_pattern, content)
+        y = re.search(y_var_pattern, content)
+
+        if x and y:
+            x = json.loads(x.group(2))
+            y = json.loads(y.group(2))
+
+            length = min(len(x), len(y))
+            x = x[:length]
+            y = y[:length]
+
+            name_match = re.search(name_pattern, trace)
+            if name_match:
+                name = name_match.group(1)
+    
+    return name, x, y

chaindl-0.1.0/chaindl/scraper/bitcoinmagazinepro.py

@@ -0,0 +1,64 @@
+import time
+import json
+import pandas as pd
+from seleniumwire import webdriver
+from selenium.webdriver.chrome.options import Options
+from seleniumwire.utils import decode
+
+def _download(url, **kwargs):
+    data = _intercept_network_requests(url, **kwargs)
+    traces = data['response']['chart']['figure']['data']
+    dfs = _create_dataframes(traces)
+    merged_df = pd.concat(dfs, axis=1, join='outer')
+    return merged_df
+
+def _create_dataframes(traces):
+    dfs = []
+    for trace in traces:
+        # if 'customdata' in trace:
+            name = trace['name']
+            x = trace['x']
+            y = trace['y']
+
+            length = min(len(x), len(y))
+            x = x[:length]
+            y = y[:length]
+
+            df = pd.DataFrame({ name: pd.to_numeric(y, errors='coerce') }, index=pd.to_datetime(pd.to_datetime(x, format='mixed').date))
+            df = df[~df.index.duplicated(keep='first')]
+            df.index.name = 'Date'
+            dfs.append(df)
+
+    return dfs
+
+def _intercept_network_requests(url, check_interval=0.5, timeout=30):
+    # Set up Chrome options for headless mode
+    chrome_options = Options()
+    chrome_options.add_argument('--headless')  # Enable headless mode
+    chrome_options.add_argument('--disable-gpu')  # Disable GPU for compatibility
+    chrome_options.add_argument('--no-sandbox')  # Bypass OS security model
+
+    driver = webdriver.Chrome(options=chrome_options)
+    driver.get(url)
+
+    start_time = time.time()
+    request = None
+
+    while time.time() - start_time < timeout:
+        for req in driver.requests:
+            if "_dash-update-component" in req.url and req.response:
+                request = req
+                break
+        if request:
+            break
+        time.sleep(check_interval)
+
+    if request:
+        content_encoding = request.response.headers.get('Content-Encoding', '')
+        body = decode(request.response.body, content_encoding)
+        body = body.decode('utf-8', errors='ignore')
+        driver.quit()
+        return json.loads(body)
+    else:
+        driver.quit()
+        raise TimeoutError(f"Could not find the request within {timeout} seconds. Try increasing the timeout!")

chaindl-0.1.0/chaindl/scraper/blockchain.py

@@ -0,0 +1,43 @@
+import requests
+import pandas as pd
+
+def _download(url, timespan="all", daysAverage="1d", include_price=True):
+    """Allowed timespans: 30days, 90days, 180days, 1year, 3years, all"""
+    metric = url.rstrip("/").split("/")[-1]
+    api_url = f"https://api.blockchain.info/charts/{metric}"
+    params = {
+        "timespan": timespan,
+        "sampled": "true",
+        "metadata": "false",
+        "daysAverageString": daysAverage,
+        "format": "json"
+    }
+    response = requests.get(api_url, params=params)
+    data = response.json()
+    if 'values' not in data or 'name' not in data:
+        raise ValueError(f"Invalid response for {metric} from Blockchain API.")
+    values = data['values']
+    name = data['name']
+
+    df = pd.DataFrame(values)
+    df = df.rename(columns={"x": "Date", "y": name or metric})
+    df['Date'] = pd.to_datetime(df['Date'], unit='s')
+    df = df.set_index("Date")
+
+    if include_price and metric != "market-price":
+        # Fetch bitcoin price
+        btc_url = "https://api.blockchain.info/charts/market-price"
+        btc_response = requests.get(btc_url, params=params)
+        btc_data = btc_response.json()
+        if 'values' not in btc_data or 'name' not in btc_data:
+            raise ValueError("Invalid response for market price from Blockchain API.")
+        btc_values = btc_data['values']
+        btc_df = pd.DataFrame(btc_values)
+        btc_df = btc_df.rename(columns={"x": "Date", "y": "Market Price (USD)"})
+        btc_df['Date'] = pd.to_datetime(btc_df['Date'], unit='s')
+        btc_df = btc_df.set_index("Date")
+
+        # Merge the dataframes on the Date index
+        df = df.merge(btc_df, left_index=True, right_index=True, how='outer')
+
+    return df

chaindl-0.1.0/chaindl/scraper/chainexposed.py

@@ -0,0 +1,35 @@
+import re
+import json
+
+import pandas as pd
+from bs4 import BeautifulSoup
+
+from . import utils
+
+def _download(url):
+    content = utils._get_page_content(url)
+    soup = BeautifulSoup(content, 'html.parser')
+    scripts = soup.find_all('script')
+
+    dfs = _extract_data_from_scripts(scripts)
+
+    merged_df = pd.concat(dfs, axis=1, join='outer')
+    return merged_df
+
+def _extract_data_from_scripts(scripts):
+    dfs = []
+
+    for script in scripts:
+        if script.string and 'Plotly.newPlot' in script.string:
+            matches = re.findall(r'var trace\d+ =\s*{\s*x:\s*(\[[^\]]*\]),\s*y:\s*(\[[^\]]*\]),.*?name:\s*\'(.*?)\'', script.string, re.DOTALL)
+            for match in matches:
+                x_data, y_data, name = match
+                name = name.replace('\\u003c', '<').replace('\\u003e', '>')
+                x = json.loads(x_data)
+                y = json.loads(y_data)
+
+                df = pd.DataFrame({ name: pd.to_numeric(y, errors='coerce') }, index=pd.to_datetime(pd.to_datetime(x).date))
+                df.index.name = 'Date'
+                dfs.append(df)
+
+    return dfs

chaindl-0.1.0/chaindl/scraper/checkonchain.py

@@ -0,0 +1,35 @@
+import re
+import json
+
+import pandas as pd
+from bs4 import BeautifulSoup
+
+from . import utils
+
+def _download(url):
+    content = utils._get_page_content(url)
+    soup = BeautifulSoup(content, 'html.parser')
+    scripts = soup.find_all('script')
+
+    dfs = _extract_data_from_scripts(scripts)
+
+    merged_df = pd.concat(dfs, axis=1, join='outer')
+    return merged_df
+
+def _extract_data_from_scripts(scripts):
+    dfs = []
+    for script in scripts:
+        if script.string and 'Plotly.newPlot' in script.string:
+            matches = re.findall(r'"name":\s*"([^"]*)"\s*,.*?"x":\s*(\[[^\]]*\])\s*,\s*"y":\s*(\[[^\]]*\])', script.string, re.DOTALL)
+            for match in matches:
+                name, x_data, y_data = match
+                name = name.replace('\\u003c', '<').replace('\\u003e', '>')
+                x = json.loads(x_data)
+                y = json.loads(y_data)
+
+                df = pd.DataFrame({ name: pd.to_numeric(y, errors='coerce') }, index=pd.to_datetime(pd.to_datetime(x, format='mixed').date))
+                df.index.name = 'Date'
+                df = df.loc[~df.index.duplicated(keep='first')] # TODO: Give user option to either choose drop dupes or take avg
+                dfs.append(df)
+
+    return dfs

chaindl-0.1.0/chaindl/scraper/cryptoquant.py

@@ -0,0 +1,101 @@
+import time
+import json
+from urllib.parse import urlparse
+from selenium import webdriver
+import pandas as pd
+
+CRYPTOQUANT_URL = "https://cryptoquant.com/"
+
+def _download(url, **kwargs):
+    email = kwargs.get('email')
+    password = kwargs.get('password')
+    if not email or not password:
+        raise TypeError("Email and/or password hasn't been passed")
+
+    splits = urlparse(url).path.split('/')
+    id = splits[-1]
+
+    # Cryptoquant's own metrics
+    if splits[1] == 'asset':
+        raise NotImplementedError("Only third party metrics on cryptoquant have been implemented.")
+
+    proxy = kwargs.get('proxy', None)
+    driver = _get_driver(proxy=proxy)
+
+    data = _get_json(driver, id, email, password)
+
+    columns = data['data']['result']['columns']
+    results = data['data']['result']['results']
+    column_names = [col['name'] for col in columns]
+
+    return _create_dataframe(results, column_names)
+
+def _create_dataframe(results, column_names):
+    df = pd.DataFrame(results, columns=column_names)
+    
+    date_column = None
+    for col in df.columns:
+        if col.lower() in ['day', 'date', 'datetime', 'transaction_day']:
+            date_column = col
+            break
+    
+    if date_column:
+        df[date_column] = pd.to_datetime(df[date_column])
+        df.set_index(date_column, inplace=True)
+        df.index.name = 'Date'
+    else:
+        print("Unable to find and parse the date column")
+    
+    return df
+
+def _get_driver(proxy=None):
+    chrome_options = webdriver.ChromeOptions()
+
+    if proxy:
+        driver = webdriver.Remote(proxy, options=chrome_options)
+    else:
+        driver = webdriver.Chrome(options=chrome_options)
+    
+    return driver
+
+def _get_json(driver, id, email, password):
+    driver.get(CRYPTOQUANT_URL)
+    time.sleep(4)
+
+    # Execute the login request
+    script = f"""
+        return fetch("https://api.cryptoquant.com/live/v1/sign-in", {{
+            method: 'POST',
+            headers: {{
+                'Content-Type': 'application/json'
+            }},
+            body: JSON.stringify({{
+                "email": "{email}",
+                "password": "{password}"
+            }})
+        }}).then(response => response.json());
+    """
+    response = driver.execute_script(script)
+
+    if 'accessToken' in response:
+        access_token = response['accessToken']
+
+        data_url = f"https://api.cryptoquant.com/live/v1/analytics/{id}"
+        
+        result_script = f"""
+            return fetch("{data_url}", {{
+                method: 'GET',
+                headers: {{
+                    'Authorization': 'Bearer {access_token}',
+                    'Accept': 'application/json'
+                }}
+            }}).then(response => response.json());
+        """
+        result = driver.execute_script(result_script)
+    else:
+        print(f"Error occurred: {response.get('error')}")
+        driver.quit()
+        return {}
+
+    driver.quit()
+    return result

chaindl-0.1.0/chaindl/scraper/utils.py

@@ -0,0 +1,9 @@
+import requests
+
+def _get_page_content(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    return response.text
+
+def _join_url(base_url, path):
+    return base_url.rstrip('/') + '/' + path.lstrip('/')