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

never use str only unicode

Browse source
This commit is contained in:
j 2008-05-23 12:48:19 +02:00
parent 6a1ecbe21c
commit 87771c6645
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
ox/imdb.py
View file

@ -96,7 +96,7 @@ def getMovieInfo(imdbId):
if not html_title: if not html_title:
html_title = soup('title') html_title = soup('title')
if html_title: if html_title:
html_title = str(html_title[0]) html_title = unicode(html_title[0])
html_title = html_title.replace('<br />', ' ').replace(' ', ' ') html_title = html_title.replace('<br />', ' ').replace(' ', ' ')
title = decodeHtml(html_title) title = decodeHtml(html_title)
title = stripTags(title) title = stripTags(title)
@ -253,7 +253,7 @@ def getMovieTrivia(imdbId):
triviaList = [] triviaList = []
for i in soup('ul', {'class': "trivia"}): for i in soup('ul', {'class': "trivia"}):
for t in i('li'): for t in i('li'):
t = str(t).replace('<br />', '').strip() t = unicode(t).replace('<br />', '').strip()
if t.startswith('<li>') and t.endswith('</li>'): if t.startswith('<li>') and t.endswith('</li>'):
t = t[4:-5].strip() t = t[4:-5].strip()
t=decodeHtml(t) t=decodeHtml(t)
@ -266,7 +266,7 @@ def getMovieConnections(imdbId):
soup = BeautifulSoup(data) soup = BeautifulSoup(data)
connections = {} connections = {}
content = soup('div', {'id': 'tn15content'})[0] content = soup('div', {'id': 'tn15content'})[0]
blocks = str(content).split('<h5>')[1:] blocks = unicode(content).split('<h5>')[1:]
for c in blocks: for c in blocks:
connection = c.split('</h5>')[0] connection = c.split('</h5>')[0]
cs = BeautifulSoup(c) cs = BeautifulSoup(c)
@ -404,7 +404,7 @@ class IMDb:
if not html_title: if not html_title:
html_title = soup('title') html_title = soup('title')
if html_title: if html_title:
html_title = str(html_title[0]) html_title = unicode(html_title[0])
html_title = stripTags(html_title) html_title = stripTags(html_title)
year = re.compile('\((\d{4})\)').findall(html_title) year = re.compile('\((\d{4})\)').findall(html_title)
if not year: if not year:
@ -446,9 +446,9 @@ class IMDb:
IMDbDict['runtime'] = 0 IMDbDict['runtime'] = 0
soup = BeautifulSoup(data) soup = BeautifulSoup(data)
for info in soup('div', {'class': 'info'}): for info in soup('div', {'class': 'info'}):
key = str(info).split('</h5>')[0].split('<h5>') key = unicode(info).split('</h5>')[0].split('<h5>')
if len(key) > 1: if len(key) > 1:
raw_value = str(info).split('</h5>')[1] raw_value = unicode(info).split('</h5>')[1]
key = key[1][:-1].lower().replace(' ', '_') key = key[1][:-1].lower().replace(' ', '_')
if key in keys: if key in keys:
IMDbDict[key] = self.parse_raw_value(key, raw_value) IMDbDict[key] = self.parse_raw_value(key, raw_value)
@ -553,7 +553,7 @@ class IMDb:
d = row('td', {'align':'right'}) d = row('td', {'align':'right'})
if d: if d:
try: try:
possible_date = stripTags(str(d[0])).strip() possible_date = stripTags(unicode(d[0])).strip()
rdate = time.strptime(possible_date, "%d %B %Y") rdate = time.strptime(possible_date, "%d %B %Y")
rdate = time.strftime('%Y-%m-%d', rdate) rdate = time.strftime('%Y-%m-%d', rdate)
return rdate return rdate
@ -568,7 +568,7 @@ class IMDb:
soup = BeautifulSoup(self.getBusiness()) soup = BeautifulSoup(self.getBusiness())
business = {'budget': 0, 'gross': 0, 'profit': 0} business = {'budget': 0, 'gross': 0, 'profit': 0}
content = soup('div', {'id': 'tn15content'})[0] content = soup('div', {'id': 'tn15content'})[0]
blocks = str(content).split('<h5>')[1:] blocks = unicode(content).split('<h5>')[1:]
for c in blocks: for c in blocks:
cs = BeautifulSoup(c) cs = BeautifulSoup(c)
line = c.split('</h5>') line = c.split('</h5>')