Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Minor Fixups #15

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Minor Fixups #15

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bb5f5f9
Normalize unicode input
sargon Nov 19, 2016
702983c
Fix variable name
sargon Nov 19, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions risscraper/scraperallris.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
import re
import sys
import time
import unicodedata

from lxml import etree, html
from lxml.cssselect import CSSSelector
Expand Down Expand Up @@ -236,7 +237,7 @@ def find_meeting(self, start_date=None, end_date=None):
""" Find meetings within a given time frame and add them to the meeting
queue.
"""
meeting_find_url = (self.config['scraper']['allris']['meeting_find_url']
meeting_find_url = ("%s/si010_j.asp?kaldatvonbis=%s-%s&selfaction=ws&template=xml&xsl=sikal1"
% (self.config['scraper']['base_url'],
start_date.strftime("%d.%m.%Y"),
end_date.strftime("%d.%m.%Y")))
Expand Down Expand Up @@ -296,7 +297,7 @@ def get_person_organization(self, person_id=None, organization_url=None):
response = self.get_url(url)
if not url:
return
tree = html.fromstring(response.text)
tree = html.fromstring(unicodedata.normalize('NFKD',response.text).encode('ascii','ignore'))

memberships = []
person = Person(originalId=person_id)
Expand Down Expand Up @@ -604,7 +605,7 @@ def get_paper(self, paper_url=None, paper_id=None):
paper_id, paper_url)
return
text = response.text
doc = html.fromstring(text)
doc = html.fromstring(unicodedata.normalize('NFKD',text).encode('ascii','ignore'))
data = {}

# Beratungsfolge-Table checken
Expand Down Expand Up @@ -883,7 +884,7 @@ def get_file(self, file_obj, file_url, post=False):
file_obj.content = file_file.content
# catch strange magic exception
try:
file.mimetype = magic.from_buffer(file_obj.content, mime=True)
file_obj.mimetype = magic.from_buffer(file_obj.content, mime=True)
except magic.MagicException:
logging.warn("Warning: unknown magic error at file %s from %s",
file_obj.originalId, file_url)
Expand Down