0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

cleanup pylint errors and py2/3 issues

Browse source
This commit is contained in:
j 2016-06-08 15:32:46 +02:00
commit 77f8876fca
20 changed files with 232 additions and 197 deletions
Download patch file Download diff file Expand all files Collapse all files

14
ox/web/spiegel.py
View file

@ -95,7 +95,7 @@ def format_subsection(string):
'ussports': 'US-Sports',
'wunderbar': 'wunderBAR'
}
if subsection.has_key(string):
if string in subsection:
return subsection[string].replace(u'\xc3', 'ae')
return string[:1].upper() + string[1:]
@ -219,8 +219,8 @@ def archive_news():
else:
dMax = days[m]
for d in range(dMax, 0, -1):
print('getNews(%d, %d, %d)' % (y, m, d))
news = getNews(y, m ,d)
print('get_news(%d, %d, %d)' % (y, m, d))
news = get_news(y, m, d)
for new in news:
dirname = archivePath + '/' + new['date'][0:4] + '/' + new['date'][5:7] + new['date'][8:10] + '/' + new['date'][11:13] + new['date'][14:16]
if not os.path.exists(dirname):
@ -230,7 +230,7 @@ def archive_news():
else:
filename = dirname + '/' + new['url'] + '.json'
if not os.path.exists(filename) or True:
data = json.dumps(new, ensure_ascii = False)
data = json.dumps(new, ensure_ascii=False)
f = open(filename, 'w')
f.write(data)
f.close()
@ -253,7 +253,7 @@ def archive_news():
string = strings[3]
if len(strings) == 6:
string += '/' + strings[4]
if not count.has_key(string):
if string not in count:
count[string] = {'count': 1, 'string': '%s %s http://www.spiegel.de/%s/0,1518,archiv-%d-%03d,00.html' % (new['date'], new['date'], new['section'].lower(), y, int(datetime(y, m, d).strftime('%j')))}
else:
count[string] = {'count': count[string]['count'] + 1, 'string': '%s %s' % (new['date'], count[string]['string'][17:])}
@ -269,12 +269,12 @@ if __name__ == '__main__':
# spiegel = Spiegel(2008, 8)
# print(spiegel.getContents())
# news = News(2001, 9, 10)
# output(news.getNews())
# output(news.get_news())
'''
x = []
for d in range(10, 30):
print('2/%d' % d)
news = getNews(2008, 2, d)
news = get_news(2008, 2, d)
for new in news:
strings = new['url'].split('/')
string = format_section(strings[3])