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

escape strings

Browse source
This commit is contained in:
j 2024-09-11 22:52:01 +01:00
commit 41edea1862
20 changed files with 74 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

14
ox/web/ubu.py
View file

@ -43,7 +43,7 @@ def get_data(url):
if not 'url' in m:
print(url, 'missing')
if 'title' in m:
m['title'] = re.sub('(.*?) \(\d{4}\)$', '\\1', m['title'])
m['title'] = re.sub(r'(.*?) \(\d{4}\)$', '\\1', m['title'])
if not 'title' in m:
match = re.compile('<span id="ubuwork">(.*?)</span>').findall(data)
@ -52,7 +52,7 @@ def get_data(url):
if not 'title' in m:
match = re.compile("<title>.*?&amp;(.*?)</title>", re.DOTALL).findall(data)
if match:
m['title'] = re.sub('\s+', ' ', match[0]).strip()
m['title'] = re.sub(r'\s+', ' ', match[0]).strip()
if ' - ' in m['title']:
m['title'] = m['title'].split(' - ', 1)[-1]
if 'title' in m:
@ -83,7 +83,7 @@ def get_data(url):
if len(txt) > 1 and txt[0].strip() == m.get('title'):
txt = txt[1:]
m['description'] = '\n\n'.join(txt).split('RESOURCES')[0].split('RELATED')[0].strip()
y = re.compile('\((\d{4})\)').findall(data)
y = re.compile(r'\((\d{4})\)').findall(data)
if y:
m['year'] = int(y[0])
d = re.compile('Director: (.+)').findall(data)
@ -98,7 +98,7 @@ def get_data(url):
if a:
m['artist'] = strip_tags(decode_html(a[0][1])).strip()
else:
a = re.compile('<b>(.*?)\(b\..*?\d{4}\)').findall(data)
a = re.compile(r'<b>(.*?)\(b\..*?\d{4}\)').findall(data)
if a:
m['artist'] = strip_tags(decode_html(a[0])).strip()
elif m['id'] == 'film/lawder_color':
@ -125,11 +125,11 @@ def get_ids():
data = read_url('http://www.ubu.com/film/')
ids = []
author_urls = []
for url, author in re.compile('<a href="(\./.*?)">(.*?)</a>').findall(data):
for url, author in re.compile(r'<a href="(\./.*?)">(.*?)</a>').findall(data):
url = 'http://www.ubu.com/film' + url[1:]
data = read_url(url)
author_urls.append(url)
for u, title in re.compile('<a href="(.*?)">(.*?)</a>').findall(data):
for u, title in re.compile(r'<a href="(.*?)">(.*?)</a>').findall(data):
if not u.startswith('http'):
if u == '../../sound/burroughs.html':
u = 'http://www.ubu.com/sound/burroughs.html'
@ -145,7 +145,7 @@ def get_ids():
def get_sound_ids():
data = read_url('http://www.ubu.com/sound/')
ids = []
for url, author in re.compile('<a href="(\./.*?)">(.*?)</a>').findall(data):
for url, author in re.compile(r'<a href="(\./.*?)">(.*?)</a>').findall(data):
url = 'http://www.ubu.com/sound' + url[1:]
ids.append(url)
ids = [get_id(url) for url in sorted(set(ids))]