mgoetz/basta-server
Archived
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix cafete parser

Browse Source
This commit is contained in:
michigg 2018-06-05 01:40:49 +02:00
parent ddf1fde2dc
commit 61187ac073
2 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ofu_app/apps/food/utils/migrate_data.py
View File

@ -117,9 +117,13 @@ def main():
logger.info("Aktueller Stand:" + writeoutDBObjects()) logger.info("Aktueller Stand:" + writeoutDBObjects())
# get food jsons # get food jsons
logger.info('AUSTRASSE')
writeStudentenwerkDataInDB(mensa_page_parser.parsePage(LINK_AUSTR_MENSA)) writeStudentenwerkDataInDB(mensa_page_parser.parsePage(LINK_AUSTR_MENSA))
logger.info('FEKI')
writeStudentenwerkDataInDB(mensa_page_parser.parsePage(LINK_FEKI_MENSA)) writeStudentenwerkDataInDB(mensa_page_parser.parsePage(LINK_FEKI_MENSA))
logger.info('ERBA')
writeStudentenwerkDataInDB(cafete_page_parser.parse_page(LINK_ERBA_CAFETE)) writeStudentenwerkDataInDB(cafete_page_parser.parse_page(LINK_ERBA_CAFETE))
logger.info('MARKUSHAUS')
writeStudentenwerkDataInDB(cafete_page_parser.parse_page(LINK_MARKUS_CAFETE)) writeStudentenwerkDataInDB(cafete_page_parser.parse_page(LINK_MARKUS_CAFETE))
writeFekideDataInDB(fekide_happyhour_page_parser.parse_page(LINK_FEKIDE_GUIDE)) writeFekideDataInDB(fekide_happyhour_page_parser.parse_page(LINK_FEKIDE_GUIDE))

9
ofu_app/apps/food/utils/parser/cafete_page_parser.py
View File

@ -8,7 +8,7 @@ from . import load_page
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
SPEISEPLAN_NAME_SELECTOR = '.csc-default .csc-header .csc-firstHeader' SPEISEPLAN_NAME_SELECTOR = '.csc-frame .csc-header .csc-firstHeader'
def get_foodplan_name(soup): def get_foodplan_name(soup):
@ -28,7 +28,7 @@ def get_right_line(lines):
def get_food_per_day(soup): def get_food_per_day(soup):
days = [] days = []
lines = soup.select('.csc-default .bodytext') lines = soup.select('.csc-frame .bodytext')
foodlines = get_right_line(lines) foodlines = get_right_line(lines)
for food in foodlines: for food in foodlines:
day = str(food).split()[0] day = str(food).split()[0]
@ -64,4 +64,7 @@ def parse_page(url: str):
logger.exception(e) logger.exception(e)
return None return None
# LINK_ERBA_CAFETE = "https://www.studentenwerk-wuerzburg.de/bamberg/essen-trinken/sonderspeiseplaene/cafeteria-erba-insel.html"
if __name__ == "__main__":
LINK_ERBA_CAFETE = "https://www.studentenwerk-wuerzburg.de/bamberg/essen-trinken/sonderspeiseplaene/cafeteria-erba-insel.html"
parse_page(LINK_ERBA_CAFETE)