0x2620/scrapeit
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

lets try utf-8

Browse source
This commit is contained in:
j 2007-06-16 16:10:34 +00:00
parent 917cbcf399
commit f666c4f61d
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
scrapeit/imdb.py
View file

@ -98,11 +98,12 @@ class IMDb:
def getPage(self, forcereload = False): def getPage(self, forcereload = False):
if forcereload or not self.pageSource: if forcereload or not self.pageSource:
self.pageSource = read_url(self.pageUrl) self.pageSource = read_url_utf8(self.pageUrl)
return self.pageSource return self.pageSource
def parse_raw_value(self, key, value): def parse_raw_value(self, key, value):
if key in ('runtime', 'language', 'genre', 'country', 'tagline', 'plot_outline'): if key in ('runtime', 'language', 'genre', 'country', 'tagline', 'plot_outline'):
value = unicode(value, 'utf-8')
value = stripTags(value).strip() value = stripTags(value).strip()
if key == 'runtime': if key == 'runtime':
parsed_value = _getTerm(value, '(.*?) min') parsed_value = _getTerm(value, '(.*?) min')