tunned-geobr 1.0.9__py3-none-any.whl → 1.0.11__py3-none-any.whl

tunned_geobr/__init__.py

@@ -130,3 +130,4 @@ from .read_ibama_embargoes import read_ibama_embargoes
 from .read_climate import read_climate
 from .read_exploration_blocks import read_exploration_blocks
 from .read_production_fields import read_production_fields
+from .read_oil_wells import read_oil_wells

tunned_geobr/list_geobr.py

@@ -140,6 +140,7 @@ def list_geobr():
         # Energy infrastructure datasets - Oil and Gas Infrastructure
         {"Function": "read_exploration_blocks", "Geography": "Oil and Gas Exploration Blocks", "Years": "All", "Source": "ANP"},
         {"Function": "read_production_fields", "Geography": "Oil and Gas Production Fields", "Years": "All", "Source": "ANP"},
+        {"Function": "read_oil_wells", "Geography": "Oil and Gas Wells", "Years": "All", "Source": "ANP"},
         {"Function": "read_fuel_bases", "Geography": "Fuel Bases", "Years": "All", "Source": "EPE"},
         {"Function": "read_glp_bases", "Geography": "GLP (LPG) Bases", "Years": "All", "Source": "EPE"},
         {"Function": "read_processing_facilities", "Geography": "Oil and Gas Processing Facilities", "Years": "All", "Source": "EPE"},

tunned_geobr/read_oil_wells.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_oil_wells(simplified=False):
+    """Download Brazilian Oil and Gas Wells data from ANP.
+    
+    This function downloads and processes the Brazilian Oil and Gas Wells data
+    from ANP (National Petroleum Agency).
+    Original source: ANP - Agência Nacional do Petróleo, Gás Natural e Biocombustíveis
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+        
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with Brazilian oil and gas wells data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_oil_wells
+    
+    # Read oil wells data
+    >>> wells = read_oil_wells()
+    """
+    
+    url = "https://gishub.anp.gov.br/geoserver/BD_ANP/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=BD_ANP%3APOCOS_SIRGAS&maxFeatures=40000&outputFormat=SHAPE-ZIP"
+    
+    try:
+        # Download the zip file
+        response = requests.get(url)
+        if response.status_code != 200:
+            raise Exception("Failed to download oil wells data from ANP")
+            
+        # 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:
+                gdf.crs = 4674
+            elif gdf.crs.to_epsg() != 4674:
+                gdf = gdf.to_crs(4674)
+            
+            if simplified:
+                # Keep only the most relevant columns
+                # Note: Column names based on typical ANP data structure
+                columns_to_keep = [
+                    'geometry',
+                    'NOME',        # Well name
+                    'OPERADOR',    # Operator
+                    'BACIA',       # Basin
+                    'CAMPO',       # Field
+                    'SITUACAO',    # Status
+                    'CATEGORIA'    # Category
+                ]
+                
+                # 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 oil wells data: {str(e)}")
+    
+    return gdf
+
+if __name__ == '__main__':
+    read_oil_wells()

tunned_geobr/read_sigel_wind_turbines.py

@@ -0,0 +1,164 @@
+import geopandas as gpd
+import os
+import tempfile
+import urllib.parse
+import requests
+import shutil
+from zipfile import ZipFile
+from pathlib import Path
+from io import BytesIO
+import warnings
+import json
+
+def read_sigel_wind_turbines(simplified=False, verbose=False):
+    """Download Wind Turbines data from Sigel.
+    
+    This function downloads and processes wind turbines data from Sigel (ANEEL).
+    Original source: ANEEL (Agência Nacional de Energia Elétrica)
+    
+    Parameters
+    ----------
+    simplified : boolean, by default False
+        If True, returns a simplified version of the dataset with fewer columns
+    verbose : boolean, by default False
+        If True, prints detailed information about the download process
+
+    Returns
+    -------
+    gpd.GeoDataFrame
+        Geodataframe with wind turbines data
+        
+    Example
+    -------
+    >>> from tunned_geobr import read_sigel_wind_turbines
+    
+    # Read wind turbines data
+    >>> wind_turbines = read_sigel_wind_turbines()
+    """
+    
+    # URL for the Sigel geoserver WFS service
+    url = r'https://sigel.aneel.gov.br/arcgis/rest/services/PORTAL/ExtractDataTaskAneel/GPServer/Extract%20Data%20Task/execute?f=json&env:outSR=102100&Layers_to_Clip=["Aerogeradores"]&Area_of_Interest={"geometryType":"esriGeometryPolygon","features":[{"geometry":{"rings":[[[-10056193.304181412,-5207437.87749587],[-10056193.304181412,2052245.3209151002],[-2405152.5209504515,2052245.3209151002],[-2405152.5209504515,-5207437.87749587],[-10056193.304181412,-5207437.87749587]]],"spatialReference":{"wkid":102100}}}],"sr":{"wkid":102100}}&Feature_Format=Shapefile - SHP - .shp&Raster_Format=Tagged Image File Format - TIFF - .tif'
+ 
+    try:
+        # Disable SSL verification warning
+        warnings.filterwarnings('ignore', message='Unverified HTTPS request')
+        
+        if verbose:
+            print("Requesting data from Sigel server...")
+            
+        response = requests.get(url, timeout=60, verify=False)
+        if not response.ok:
+            raise Exception(f"Error getting JSON response: {response.status_code}")
+
+        json_response = response.json()
+        
+        if verbose:
+            print(f"JSON response received: {json.dumps(json_response, indent=2)[:500]}...")
+            
+        if 'results' not in json_response or len(json_response['results']) == 0:
+            raise Exception("Invalid JSON response structure")
+            
+        if 'value' not in json_response['results'][0] or 'url' not in json_response['results'][0]['value']:
+            raise Exception("URL not found in JSON response")
+            
+        file_url = json_response['results'][0]['value']['url']
+        
+        if verbose:
+            print(f"Downloading file from: {file_url}")
+        
+        file_response = requests.get(file_url, stream=True, timeout=60, verify=False)
+        if not file_response.ok:
+            raise Exception(f"Error downloading file: {file_response.status_code}")
+        
+        # Check if content is actually a zip file
+        content = file_response.content
+        if len(content) < 100:
+            if verbose:
+                print(f"Warning: Downloaded content is very small ({len(content)} bytes)")
+                print(f"Content preview: {content[:100]}")
+            
+        # Create a temporary directory to extract the files
+        with tempfile.TemporaryDirectory() as temp_dir:
+            if verbose:
+                print(f"Extracting files to temporary directory: {temp_dir}")
+                
+            try:
+                # Extract the zip file
+                with ZipFile(BytesIO(content)) as zip_ref:
+                    zip_ref.extractall(temp_dir)
+                    
+                    if verbose:
+                        print(f"Files in zip: {zip_ref.namelist()}")
+            except Exception as zip_error:
+                if verbose:
+                    print(f"Error extracting zip: {str(zip_error)}")
+                    print(f"Saving content to debug.zip for inspection")
+                    with open("debug.zip", "wb") as f:
+                        f.write(content)
+                raise Exception(f"Failed to extract zip file: {str(zip_error)}")
+            
+            # Find the shapefile
+            all_files = os.listdir(temp_dir)
+            if verbose:
+                print(f"Files in temp directory: {all_files}")
+                
+            shp_files = [f for f in all_files if f.endswith('.shp')]
+            if not shp_files:
+                # Try looking in subdirectories
+                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
+            shp_path = shp_files[0] if os.path.isabs(shp_files[0]) else os.path.join(temp_dir, shp_files[0])
+            if verbose:
+                print(f"Reading shapefile: {shp_path}")
+                
+            gdf = gpd.read_file(shp_path)
+            
+            # Convert to SIRGAS 2000 (EPSG:4674)
+            gdf = gdf.to_crs(4674)
+            
+            if verbose:
+                print(f"Data loaded successfully with {len(gdf)} records")
+                print(f"Columns: {gdf.columns.tolist()}")
+            
+            if simplified:
+                # Keep only the most relevant columns based on actual data structure
+                columns_to_keep = [
+                    'geometry',
+                    # Add relevant columns for wind turbines here, e.g.,
+                    # 'nome',       # Plant name
+                    # 'potencia',   # Power capacity
+                    # 'leilao',     # Auction
+                    # 'ceg',        # CEG code
+                    # 'ano_prev'    # Expected year
+                ]
+                
+                # Filter columns that actually exist in the dataset
+                existing_columns = ['geometry'] + [col for col in columns_to_keep[1:] if col in gdf.columns]
+                if len(existing_columns) <= 1:
+                    if verbose:
+                        print("Warning: No matching columns found for simplified version. Returning all columns.")
+                else:
+                    gdf = gdf[existing_columns]
+    
+    except Exception as e:
+        raise Exception(f"Error downloading or processing wind turbines data: {str(e)}")
+        
+    return gdf
+
+if __name__ == '__main__':
+    try:
+        wind_turbines_data = read_sigel_wind_turbines(verbose=True)
+        print(f"Downloaded wind turbines data with {len(wind_turbines_data)} records and {len(wind_turbines_data.columns)} columns")
+        
+        # Test simplified version
+        simplified_data = read_sigel_wind_turbines(simplified=True)
+        print(f"Simplified data has {len(simplified_data.columns)} columns: {simplified_data.columns.tolist()}")
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        import traceback
+        traceback.print_exc()

{tunned_geobr-1.0.9.dist-info → tunned_geobr-1.0.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tunned-geobr
-Version: 1.0.9
+Version: 1.0.11
 Summary: Fork personalizado do geobr com funcionalidades extras como download de dados da ANM
 Author: Anderson Stolfi
 License: MIT

{tunned_geobr-1.0.9.dist-info → tunned_geobr-1.0.11.dist-info}/RECORD

@@ -1,10 +1,10 @@
-tunned_geobr-1.0.9.dist-info/METADATA,sha256=9kwtRWvanWUDEw9kf_cxgQfNxKlT5zt9p0Z1f02QVDQ,5018
-tunned_geobr-1.0.9.dist-info/WHEEL,sha256=tSfRZzRHthuv7vxpI4aehrdN9scLjk-dCJkPLzkHxGg,90
-tunned_geobr-1.0.9.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
-tunned_geobr-1.0.9.dist-info/licenses/LICENSE.txt,sha256=mECZRcbde3HssOKe1Co4zgqBLGVN0OWpTsEy3LIbcRA,75
-tunned_geobr/__init__.py,sha256=b2xOTqV-FDT-L-Tc3Us1c_XydiHF-HEqAKTbSvWXCEo,7552
+tunned_geobr-1.0.11.dist-info/METADATA,sha256=-OD5dmaWBgTi2LdFztCAK1lC9T7Ry8TFHnqMoiUJ7wM,5019
+tunned_geobr-1.0.11.dist-info/WHEEL,sha256=tSfRZzRHthuv7vxpI4aehrdN9scLjk-dCJkPLzkHxGg,90
+tunned_geobr-1.0.11.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+tunned_geobr-1.0.11.dist-info/licenses/LICENSE.txt,sha256=mECZRcbde3HssOKe1Co4zgqBLGVN0OWpTsEy3LIbcRA,75
+tunned_geobr/__init__.py,sha256=FU_YkEkjkMlq6J2AxEV8WQLFFiGDIXj37Vyjz_hWNdQ,7595
 tunned_geobr/data/grid_state_correspondence_table.csv,sha256=FpkBuX_-lRXQ1yBrQODxQgG9oha9Fd8A8zGKfdsDAmk,2660
-tunned_geobr/list_geobr.py,sha256=n7bAi7O4QYdceAsfhI9M4mJ7zP1SbO5YS8iT1MQ-d9M,17654
+tunned_geobr/list_geobr.py,sha256=MaPOra0n2wPuakB-IPwK33x9uyXCWH5sjDb3D7eIQhk,17761
 tunned_geobr/lookup_muni.py,sha256=ny1zU4i6OagvL4Mrc6XQWPgn2RrJa_mXlKXh81oVYsM,3462
 tunned_geobr/read_ama_anemometric_towers.py,sha256=M3qKBTBYdqHzTuWtRrBiLA88Ymt6g0cf7sakJd5mTRo,4686
 tunned_geobr/read_amazon.py,sha256=HiwKnYebWe3nDMDRUqHpKJIO76bA4ERm4iJlCPhagQg,1286
@@ -96,6 +96,7 @@ tunned_geobr/read_og_probabilistic_effective_basin.py,sha256=ftdY--3rZJwhCfbuQUL
 tunned_geobr/read_og_total_ipa.py,sha256=0Tz4x7ZD7bRvXiLR2AitAmx-hQEVxAzNugfg2o0L3gc,5300
 tunned_geobr/read_og_unconventional_resources.py,sha256=97lUpkJQtBZTUb4oPdvT9wxlm2yj6euWzLR4oGiezrc,5444
 tunned_geobr/read_oil_and_derivatives_terminal.py,sha256=-BzLd9WpWWgH1pUaz9y16rg54FbZgUqJ_YTqbFak_7Y,5385
+tunned_geobr/read_oil_wells.py,sha256=WeM4OY1x3KSdmdY2hQqCxlcvYySmsaCaICplRxulNUg,3080
 tunned_geobr/read_pan_strategic_areas 2.py,sha256=alORMUQbnW_ER3_uOzqTbUaSyr-Y3Mg_bsoykxiGDMA,2654
 tunned_geobr/read_pan_strategic_areas.py,sha256=EP-Qtx_q4lE3lsNNIUaoQc5j-9aKBkxY2BizTwWY3ZY,3375
 tunned_geobr/read_pedology.py,sha256=xk_yOxIOVTHip4kj2y1xgO4fHKn8e1dv2cNOayXCtKk,2783
@@ -126,6 +127,7 @@ tunned_geobr/read_sedimentary_basins.py,sha256=mpCde4-WRdAAuHF-AwrODd0GpxRhzJOuP
 tunned_geobr/read_semiarid.py,sha256=pxxYTWq8_UPUyblA7_FXXXRz-XOCrrebCvYQ-kgDSrU,1358
 tunned_geobr/read_settlements.py,sha256=C47Wj4DhSDa-pSFfYK4uGDwtu4sUwqPMr-CuuxS95xg,3060
 tunned_geobr/read_sigef_properties.py,sha256=rYdh8o_fhXom1A9wQsd5d9dKhT02wTpGRY2ACTpQZ4A,4735
+tunned_geobr/read_sigel_wind_turbines.py,sha256=uobMxbB4M_npQfoGGkYKuImoFxaNy_OpNT1ZDLlUjzs,7112
 tunned_geobr/read_snci_properties.py,sha256=80VUN5NesYiNTfioaw7aybLHDNpYJObQT-kV90big-c,3233
 tunned_geobr/read_state.py,sha256=JgV3cR0LFbmwIzuzPbR_Zfy1bR_2eBeEPxunozctuag,3819
 tunned_geobr/read_state_direct.py,sha256=8Tdz-gVH_t90BJngcfcpr0VLs5HfCUxRgRQj8hy4Bt0,3826
@@ -140,4 +142,4 @@ tunned_geobr/read_water_bodies_ana.py,sha256=Z-dpTPVgRHVndTeSFxx8uXn7ufMg2jm0Dlz
 tunned_geobr/read_waterways.py,sha256=mEdoVogYWr5EYZ8bE3xMCVWyLrHYU7xTL2lUE0XbDAM,2951
 tunned_geobr/read_weighting_area.py,sha256=m2X5Ua3jRqLlkqCQbIzR2jmo58pzqkyR3UYcGtgy20E,2325
 tunned_geobr/utils.py,sha256=WT9PSGWvcERjj3yhfTvyWSE5ZiEjO4tYK5xIj5jJCg8,8170
-tunned_geobr-1.0.9.dist-info/RECORD,,
+tunned_geobr-1.0.11.dist-info/RECORD,,