gistfile1.txt

Attempting an entry for Raul Ruiz
Ruiz
Traceback (most recent call last):
  File "manage.py", line 10, in <module>
    execute_from_command_line(sys.argv)
  File "/home/vagrant/.virtualenvs/politracker/local/lib/python2.7/site-packages/django/core/management/__init__.py", line 385, in execute_from_command_line
    utility.execute()
  File "/home/vagrant/.virtualenvs/politracker/local/lib/python2.7/site-packages/django/core/management/__init__.py", line 377, in execute
    self.fetch_command(subcommand).run_from_argv(self.argv)
  File "/home/vagrant/.virtualenvs/politracker/local/lib/python2.7/site-packages/django/core/management/base.py", line 288, in run_from_argv
    self.execute(*args, **options.__dict__)
  File "/home/vagrant/.virtualenvs/politracker/local/lib/python2.7/site-packages/django/core/management/base.py", line 338, in execute
    output = self.handle(*args, **options)
  File "/home/vagrant/politracker/finder/management/commands/pic_scrape.py", line 26, in handle
    self.create_or_update(leg)
  File "/home/vagrant/politracker/finder/management/commands/pic_scrape.py", line 30, in create_or_update
    leg['last_name']))
UnicodeEncodeError: 'ascii' codec can't encode character u'\xe1' in position 1: ordinal not in range(128)

pic_scrape.py

from django.core.management.base import BaseCommand, CommandError

from bs4 import BeautifulSoup
import requests
import sunlight

from politracker.settings import base
from finder.models import Legislator

sunlight.config.API_KEY = base.SUNLIGHT_API


class Command(BaseCommand):
    def add_arguments(self, parser):
        parser.add_argument('--bioguide',
                            type=str,
                            help="Bioguide ID for a specific representative to update",
                            dest='bioguide')

    def handle(self, *args, **options):
        if options.get('bioguide', False):
            legs = [sunlight.congress.legislator(options['bioguide'])]
        else:
            legs = sunlight.congress.all_legislators_in_office()
        for leg in legs:
            self.create_or_update(leg)

    def create_or_update(self, leg):
        self.stdout.write("Attempting an entry for {} {}".format(leg['first_name'],
                                                         leg['last_name']))
        obj, created = Legislator.objects.get_or_create(
            bioguide_id=leg['bioguide_id'],
            defaults={
                'first_name': leg['first_name'],
                'last_name': leg['last_name'],
                'congress_image_url': scrape_congress_image_url(leg['first_name'],
                                                                leg['last_name'],
                                                                leg['bioguide_id']),
                }
            )
        if created:
            self.stdout.write("Created a new entry for {} {}".format(leg['first_name'],
                                                         leg['last_name']))
        else:
            self.stdout.write("Updating image url for {} {}".format(leg['first_name'], leg['last_name']))
            obj.congress_image_url = scrape_congress_image_url(leg['first_name'],
                                                               leg['last_name'],
                                                               leg['bioguide_id'])
            obj.save()

def scrape_congress_image_url(firstname, lastname, bioguide):
    page = requests.get('https://www.congress.gov/member/{}-{}/{}'.format(firstname, lastname, bioguide))
    soup = BeautifulSoup(page.text, "html.parser")
    try:
        img = soup.find('div', attrs={'class': 'member_picture'}).a.get('href')
        return 'https://www.congress.gov/{}'.format(img)
    except AttributeError:
        # Some members don't have photos, so we'll skip those.
        return 'http://2.bp.blogspot.com/-6QyJDHjB5XE/Uscgo2DVBdI/AAAAAAAACS0/DFSFGLBK_fY/s1600/facebook-default-no-profile-pic.jpg'