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

get rid of u string literal

Browse source
This commit is contained in:
j 2023-07-27 18:12:13 +02:00
commit 99e221095b
7 changed files with 98 additions and 98 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ox/web/criterion.py
View file

@ -19,13 +19,13 @@ def get_url(id):
def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
'''
>>> get_data('1333').get('imdbId')
u'0060304'
'0060304'
>>> get_data('236')['posters'][0]
u'http://s3.amazonaws.com/criterion-production/release_images/1586/ThirdManReplace.jpg'
'http://s3.amazonaws.com/criterion-production/release_images/1586/ThirdManReplace.jpg'
>>> get_data('786')['posters'][0]
u'http://s3.amazonaws.com/criterion-production/product_images/185/343_box_348x490.jpg'
'http://s3.amazonaws.com/criterion-production/product_images/185/343_box_348x490.jpg'
'''
data = {
"id": id,
@ -39,7 +39,7 @@ def get_data(id, timeout=ox.cache.cache_timeout, get_imdb=False):
data["number"] = find_re(html, "<b>Spine #(\d+)")
data["title"] = decode_html(find_re(html, "<h1 class=\"header__primarytitle\".*?>(.*?)</h1>"))
data["title"] = data["title"].split(u' \u2014 The Television Version')[0].strip()
data["title"] = data["title"].split(' \u2014 The Television Version')[0].strip()
results = find_re(html, '<ul class="film-meta-list">(.*?)</ul>')
info = re.compile('<li itemprop="(.*?)".*?>(.*?)</li>', re.DOTALL).findall(results)
info = {k: strip_tags(v).strip() for k, v in info}