near/berliner-winter
1
0
Fork 0
mirror of https://github.com/heyarne/berliner-winter.git synced 2026-05-06 19:23:39 +02:00
Code Issues Projects Releases Wiki Activity

Remove field 'addtional_place' because it can't be reliably parsed

Browse source
This commit is contained in:
Arne Schlüter 2014-12-11 00:07:48 +01:00
commit 98d1e21a90
3 changed files with 4 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

12
scraper/scraper.py
View file

@ -42,22 +42,14 @@ class Scraper():
print('Failed for headline ' + headline)
raise
places = headline[headline.find(' ') + 1:]
if places.find(' ') == -1:
district = places
additional = None
else:
district = places[:places.find(' ')]
additional = places[places.find(' ') + 1:].strip()
place = headline[headline.find(' ') + 1:]
text = table.select('tr')[2].select('td')[1].get_text()
article = {
'date': date(int(year), int(month), int(day) if day else 1),
'month_only': day is None,
'place': district.strip(),
'additional_place': additional,
'place': place.strip(),
'description': text.strip()
}
articles.append(article)