Atenea/extraccion
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Validación de materias actuales

Browse Source
This commit is contained in:
Alejandro Lara
2025-06-25 21:03:16 +00:00
parent eeba26b672
commit b83b061d5b
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
app.py
View File

@@ -156,15 +156,19 @@ def extract(driver, username: str, password: str):
# Obtener el HTML de las materias
materias_html = driver.find_element(By.ID, 'ctl00_contenedor_HistorialAlumno1_divHAcademico').get_attribute('innerHTML')
historial_html = driver.find_element(By.ID, 'ctl00_contenedor_HistorialAlumno1_gvMaterias').get_attribute('innerHTML')
materias_actuales_html = driver.find_element(By.ID, 'ctl00_contenedor_HistorialAlumno1_gvMatOrdinario').get_attribute('innerHTML')
# Materias actuales
try:
materias_actuales_html = driver.find_element(By.ID, 'ctl00_contenedor_HistorialAlumno1_gvMatOrdinario').get_attribute('innerHTML')
materias_html_io = StringIO(f"<table>{materias_actuales_html}</table>")
df_materias = pd.read_html(materias_html_io)[0]
df_materias = df_materias.drop(columns=['Unnamed: 0', 'Seleccionar'], errors='ignore')
except NoSuchElementException:
df_materias = pd.DataFrame()
# Manejar el historial como DataFrame
historial_html_io = StringIO(f"<table>{historial_html}</table>")
materias_html_io = StringIO(f"<table>{materias_actuales_html}</table>")
df = pd.read_html(historial_html_io)[0]
df_materias = pd.read_html(materias_html_io)[0]
df_materias = df_materias.drop(columns=['Unnamed: 0', 'Seleccionar'])
json_result = None
json_materias = None