tunned-geobr 0.1.2__py3-none-any.whl → 0.2.0__py3-none-any.whl

tunned_geobr/read_snci_properties.py

@@ -0,0 +1,83 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_snci_properties(simplified=False):
+    """Download Certified Properties data from INCRA's SNCI.
+    
+    This function downloads and processes certified properties data from INCRA's 
+    National Property Certification System (Sistema Nacional de Certificação de Imóveis - SNCI). 
+    The data includes information about certified rural properties across Brazil.
+    Original source: INCRA (Instituto Nacional de Colonização e Reforma Agrária)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with certified properties data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_snci_properties
+    
+    # Read certified properties data
+    >>> properties = read_snci_properties()
+    """
+    
+    url = "https://certificacao.incra.gov.br/csv_shp/zip/Imóvel%20certificado%20SNCI%20Brasil.zip"
+    if 1==1:
+        return "Essa camada está muito pesada, baixe manualmente no link: " + url
+    try:
+        # Download the zip file
+        # Disable SSL verification due to INCRA's certificate issues
+        import urllib3
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        
+        response = requests.get(url, verify=False)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from INCRA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = [f for f in os.listdir(temp_dir) if f.endswith('.shp')]
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(os.path.join(temp_dir, shp_files[0]))
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'parcela',      # Property ID
+                    'municipio',    # Municipality
+                    'uf',          # State
+                    'area_ha',     # Area in hectares
+                    'status',      # Certification status
+                    'data_cert',   # Certification date
+                    'cod_imovel',  # Property code
+                    'nome_imov'    # Property name
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading certified properties data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_state_direct.py

@@ -0,0 +1,103 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_state(code_state="all", simplified=True):
+    """Download shapefiles of Brazilian states as geopandas objects.
+
+    This function downloads and processes state data directly from IBGE (Brazilian Institute of Geography and Statistics).
+    Data uses Geodetic reference system "SIRGAS2000" and CRS(4674).
+    
+    Parameters
+    ----------
+    code_state : str, optional
+        The two-digit code of a state or a two-letter uppercase abbreviation
+        (e.g. 33 or "RJ"). If code_state="all", all states will be loaded (Default).
+    simplified : boolean, by default True
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with state boundaries
+
+    Example
+    -------
+    >>> from tunned_geobr import read_state
+
+    # Read all states
+    >>> states = read_state()
+
+    # Read specific state by code
+    >>> state = read_state(code_state=33)
+
+    # Read specific state by abbreviation
+    >>> state = read_state(code_state="RJ")
+    """
+    
+    url = "https://geoftp.ibge.gov.br/organizacao_do_territorio/malhas_territoriais/malhas_municipais/municipio_2023/Brasil/BR_UF_2023.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download state data from IBGE")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            # Filter by code_state if not "all"
+            if code_state != "all":
+                if isinstance(code_state, int) or code_state.isdigit():
+                    # Filter by numeric code
+                    code = str(code_state).zfill(2)
+                    gdf = gdf[gdf['CD_UF'] == code]
+                elif isinstance(code_state, str) and len(code_state) == 2:
+                    # Filter by state abbreviation
+                    gdf = gdf[gdf['SIGLA_UF'] == code_state.upper()]
+                
+                if len(gdf) == 0:
+                    raise Exception(f"No data found for code_state={code_state}")
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'CD_UF',       # State code
+                    'SIGLA_UF',    # State abbreviation
+                    'NM_UF',       # State name
+                    'AREA_KM2'     # Area in square kilometers
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading state data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_state()

tunned_geobr/read_state_highways.py

@@ -0,0 +1,79 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_state_highways(simplified=False):
+    """Download State Highways data from MapBiomas.
+    
+    This function downloads and processes state highways data from MapBiomas. 
+    The data includes information about state-managed highways across Brazil.
+    Original source: MapBiomas
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with state highways data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_state_highways
+    
+    # Read state highways data
+    >>> highways = read_state_highways()
+    """
+    
+    url = "https://brasil.mapbiomas.org/wp-content/uploads/sites/4/2023/08/rodovia-estadual.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from MapBiomas")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'sigla',        # Highway code
+                    'uf',           # State
+                    'jurisdicao',   # Jurisdiction
+                    'superficie',   # Surface type
+                    'situacao',     # Status
+                    'extensao_km',  # Length in km
+                    'tipo_trecho'   # Section type
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading state highways data: {str(e)}")
+        
+    return gdf

tunned_geobr/read_transmission_lines_ons.py

@@ -0,0 +1,87 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_transmission_lines_ons(simplified=False):
+    """Download Brazilian Transmission Lines data from ONS.
+    
+    This function downloads and processes the Brazilian Transmission Lines data
+    from ONS (National Electric System Operator).
+    Original source: ONS - Operador Nacional do Sistema Elétrico
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian transmission lines data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_transmission_lines_ons
+    
+    # Read transmission lines data
+    >>> transmission_lines = read_transmission_lines_ons()
+    """
+    
+    # The URL provided is a blob URL which might be temporary
+    # This is the permanent URL to the ONS data portal
+    url = "https://sig.ons.org.br/download/LT_SIN.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download transmission lines data from ONS")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names may need adjustment based on actual data
+                columns_to_keep = [
+                    'geometry',
+                    'NOME',        # Line name
+                    'TENSAO',      # Voltage
+                    'EXTENSAO',    # Length
+                    'CIRCUITO',    # Circuit
+                    'PROPRIETAR',  # Owner
+                    'STATUS'       # Status
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading transmission lines data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_transmission_lines_ons()

tunned_geobr/read_vegetation.py

@@ -0,0 +1,84 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_vegetation(simplified=False):
+    """Download Brazilian Vegetation data from IBGE.
+    
+    This function downloads and processes the Brazilian Vegetation data at 1:250,000 scale
+    from IBGE (Brazilian Institute of Geography and Statistics).
+    Original source: IBGE - Instituto Brasileiro de Geografia e Estatística
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian vegetation data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_vegetation
+    
+    # Read vegetation data
+    >>> vegetation = read_vegetation()
+    """
+    
+    url = "https://geoftp.ibge.gov.br/informacoes_ambientais/vegetacao/vetores/escala_250_mil/versao_2023/vege_area.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download vegetation data from IBGE")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names may need adjustment based on actual data
+                columns_to_keep = [
+                    'geometry',
+                    'NOME',        # Vegetation name
+                    'TIPO',        # Vegetation type
+                    'REGIAO',      # Region
+                    'BIOMA',       # Biome
+                    'AREA_KM2'     # Area in square kilometers
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading vegetation data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_vegetation()

tunned_geobr/read_water_bodies_ana.py

@@ -0,0 +1,87 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_water_bodies_ana(simplified=False):
+    """Download Brazilian Water Bodies data from ANA.
+    
+    This function downloads and processes the Brazilian Water Bodies data
+    from ANA (National Water Agency). The data includes lakes, reservoirs, and other water bodies.
+    Original source: ANA - Agência Nacional de Águas e Saneamento Básico
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian water bodies data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_water_bodies_ana
+    
+    # Read water bodies data
+    >>> water_bodies = read_water_bodies_ana()
+    """
+    
+    url = "https://metadados.snirh.gov.br/files/7d054e5a-8cc9-403c-9f1a-085fd933610c/geoft_bho_massa_dagua_v2019.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download water bodies data from ANA")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            
+            # Convert to SIRGAS 2000 (EPSG:4674) if not already
+            if gdf.crs is None or gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names may need adjustment based on actual data
+                columns_to_keep = [
+                    'geometry',
+                    'nome',        # Water body name
+                    'tipo',        # Type of water body
+                    'area_km2',    # Area in square kilometers
+                    'cocursodag',  # Water course code
+                    'cobacia',     # Basin code
+                    'nuareacont',  # Contribution area
+                    'nuvolumehm',  # Volume in cubic hectometers
+                    'dsoperacao'   # Operation status
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading water bodies data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    read_water_bodies_ana()

tunned_geobr/read_waterways.py

@@ -0,0 +1,80 @@
+import geopandas as gpd
+import tempfile
+import os
+import requests
+from zipfile import ZipFile
+from io import BytesIO
+
+def read_waterways(simplified=False):
+    """Download Waterways data from SNIRH.
+    
+    This function downloads and processes waterways data from SNIRH (National Water Resources Information System). 
+    The data includes information about navigable waterways across Brazil.
+    Original source: SNIRH (Sistema Nacional de Informações sobre Recursos Hídricos)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with waterways data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_waterways
+    
+    # Read waterways data
+    >>> waterways = read_waterways()
+    """
+    
+    url = "https://metadados.snirh.gov.br/geonetwork/srv/api/records/48e26e99-db01-45dc-a270-79f27680167b/attachments/GEOFT_TRECHO_HIDROVIARIO.zip"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download data from SNIRH")
+            
+        # Create a temporary directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Extract the zip file
+            with ZipFile(BytesIO(response.content)) as zip_ref:
+                zip_ref.extractall(temp_dir)
+            
+            # Find the shapefile
+            shp_files = []
+            for root, dirs, files in os.walk(temp_dir):
+                shp_files.extend([os.path.join(root, f) for f in files if f.endswith('.shp')])
+            
+            if not shp_files:
+                raise Exception("No shapefile found in the downloaded data")
+                
+            # Read the shapefile
+            gdf = gpd.read_file(shp_files[0])
+            gdf = gdf.to_crs(4674)  # Convert to SIRGAS 2000
+            
+            if simplified:
+                # Keep only the most relevant columns
+                columns_to_keep = [
+                    'geometry',
+                    'nome',            # Waterway name
+                    'hidrovia',        # Waterway system
+                    'rio',            # River name
+                    'situacao',       # Status
+                    'extensao_km',    # Length in km
+                    'administra',     # Administration
+                    'regime',         # Water regime
+                    'classifica'      # Classification
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading waterways data: {str(e)}")
+        
+    return gdf

{tunned_geobr-0.1.2.dist-info → tunned_geobr-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tunned-geobr
-Version: 0.1.2
+Version: 0.2.0
 Summary: Fork personalizado do geobr com funcionalidades extras como download de dados da ANM
 Author: Anderson Stolfi
 License: MIT
@@ -20,6 +20,8 @@ Requires-Dist: lxml<6.0.0,>=5.1.0
 Requires-Dist: html5lib==1.1
 Requires-Dist: geobr<0.3.0,>=0.2.2
 Requires-Dist: patool>=1.15.0
+Requires-Dist: fiona>=1.10.1
+Requires-Dist: gdown>=5.2.0
 Description-Content-Type: text/markdown
 
 # geobr: Download Official Spatial Data Sets of Brazil 
@@ -59,8 +61,40 @@ It adds:
 
 ! Be aware that if the function that you are adding is more complicated than the template. So, always double check !
 
+## System Dependencies
 
+Some functions in geobr require additional system tools to be installed:
 
+### For RAR file extraction (`read_baze_sites`)
+
+This function requires one of the following tools to be installed:
+
+- **unrar**: 
+  - macOS: `brew install unrar`
+  - Ubuntu/Debian: `sudo apt-get install unrar`
+  - Windows: Install WinRAR
+
+- **unar**:
+  - macOS: `brew install unar`
+  - Ubuntu/Debian: `sudo apt-get install unar`
+  - Windows: Install The Unarchiver
+
+- **7-Zip**:
+  - macOS: `brew install p7zip`
+  - Ubuntu/Debian: `sudo apt-get install p7zip-full`
+  - Windows: Install 7-Zip
+
+### For ZIP file extraction (IBGE files)
+
+Some IBGE files use compression methods not supported by Python's built-in zipfile module. The following functions use the system's `unzip` command:
+
+- `read_census_tract_2022`
+- `read_neighborhoods_2022`
+
+Make sure you have the `unzip` command available on your system:
+- macOS: Typically pre-installed
+- Ubuntu/Debian: `sudo apt-get install unzip`
+- Windows: Install a tool like 7-Zip or add unzip via WSL
 
 ## Translation Status
 
@@ -94,10 +128,8 @@ It adds:
 | lookup_muni               | Yes         | No    |
 | read_neighborhood         | Yes         | Yes   |
 
-
 # Release new version
 
 ```
 poetry version [patch|minor|major]
 poetry publish --build
-```