diff options
Diffstat (limited to 'parsers/people.py')
| -rw-r--r-- | parsers/people.py | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/parsers/people.py b/parsers/people.py index 265dacc..e05c5a3 100644 --- a/parsers/people.py +++ b/parsers/people.py @@ -4,7 +4,7 @@ from django.conf import settings import troggle.core.models as models import csv, re, datetime, os, shutil from utils import save_carefully -from HTMLParser import HTMLParser +from html.parser import HTMLParser from unidecode import unidecode # def saveMugShot(mugShotPath, mugShotFilename, person): @@ -45,7 +45,7 @@ def parseMugShotAndBlurb(personline, header, person): #Only finds the first image, not all of them person.blurb=re.search('<body>.*<hr',personPageOld,re.DOTALL).group() else: - print "ERROR: --------------- Broken link or Blurb parse error in ", mugShotFilename + print("ERROR: --------------- Broken link or Blurb parse error in ", mugShotFilename) #for mugShotFilename in re.findall('i/.*?jpg',personPageOld,re.DOTALL): # mugShotPath = os.path.join(settings.EXPOWEB, "folk", mugShotFilename) # saveMugShot(mugShotPath=mugShotPath, mugShotFilename=mugShotFilename, person=person) @@ -55,8 +55,8 @@ def LoadPersonsExpos(): persontab = open(os.path.join(settings.EXPOWEB, "folk", "folk.csv")) personreader = csv.reader(persontab) - headers = personreader.next() - header = dict(zip(headers, range(len(headers)))) + headers = next(personreader) + header = dict(list(zip(headers, list(range(len(headers)))))) # make expeditions print(" - Loading expeditions") @@ -100,7 +100,7 @@ def LoadPersonsExpos(): parseMugShotAndBlurb(personline=personline, header=header, person=person) # make person expedition from table - for year, attended in zip(headers, personline)[5:]: + for year, attended in list(zip(headers, personline))[5:]: expedition = models.Expedition.objects.get(year=year) if attended == "1" or attended == "-1": lookupAttribs = {'person':person, 'expedition':expedition} |