本文整理汇总了Python中resources.lib.modules.cleantitle.normalize函数的典型用法代码示例。如果您正苦于以下问题：Python normalize函数的具体用法？Python normalize怎么用？Python normalize使用的例子？那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了normalize函数的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: searchMovie
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title)))
r = self.s.get(url, headers=headers).content
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title'))
r = [(i[0], i[1], re.findall('(\d+)', i[0])[0]) for i in r]
results = []
for i in r:
try:
info = client.request(urlparse.urljoin(self.base_link, self.info_link % i[2]), headers=headers, timeout='15')
y = re.findall('<div\s+class="jt-info">(\d{4})', info)[0]
if self.matchAlias(i[1], aliases) and (year == y):
url = i[0]
break
#results.append([i[0], i[1], re.findall('<div\s+class="jt-info">(\d{4})', info)[0]])
except:
url = None
pass
#try:
# r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0]
# url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0]
#except:
# url = None
# pass
if (url == None):
url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0]
return url
except:
return示例2: movie
def movie(self, imdb, title, localtitle, aliases, year):
try:
url = self.moviesearch_link % cleantitle.geturl(title)
r = urlparse.urljoin(self.base_link, url)
r = client.request(r, limit='1', timeout='10')
r = client.parseDOM(r, 'title')
if not r:
url = 'http://www.imdb.com/title/%s' % imdb
url = client.request(url, headers={'Accept-Language':'es-ES'}, timeout='10')
url = client.parseDOM(url, 'title')[0]
url = re.sub('(?:\(|\s)\d{4}.+', '', url).strip()
url = cleantitle.normalize(url.encode("utf-8"))
url = self.moviesearch_link % cleantitle.geturl(url)
r = urlparse.urljoin(self.base_link, url)
r = client.request(r, limit='1', timeout='10')
r = client.parseDOM(r, 'title')
if not year in r[0]: raise Exception()
return url
except:
pass示例3: searchShow
def searchShow(self, title, season, year, aliases, headers):
try:
title = cleantitle.normalize(title)
t = cleantitle.get(title)
url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.query('%s Season %01d' % (title.replace('\'', '-'), int(season)))))
r = client.request(url, timeout='10')
r = client.parseDOM(r, 'h2', attrs={'class': 'tit'})
if r:
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title')) for i in r]
r = [(i[0][0], i[1][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0]
r = [(i[0], re.findall('(.+?)\s+-\s+Season\s+(\d+)', i[1])) for i in r]
r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0]
r = [i[0] for i in r if t == cleantitle.get(i[1]) and int(season) == int(i[2])][0]
else:
url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.query('%s %01d' % (title.replace('\'', '-'), int(year)))))
r = client.request(url, timeout='10')
r = client.parseDOM(r, 'h2', attrs={'class': 'tit'})
r = [(client.parseDOM(i, 'a', ret='href'), client.parseDOM(i, 'a', ret='title')) for i in r]
r = [(i[0][0], i[1][0]) for i in r if len(i[0]) > 0 and len(i[1]) > 0]
r = [(i[0], re.findall('(.+?) \((\d{4})', i[1])) for i in r]
r = [(i[0], i[1][0][0], i[1][0][1]) for i in r if len(i[1]) > 0]
r = [i[0] for i in r if t == cleantitle.get(i[1]) and year == i[2]][0]
url = re.findall('(?://.+?|)(/.+)', r)[0]
url = client.replaceHTMLCodes(url)
return url.encode('utf-8')
except:
return示例4: tvshow
def tvshow(self, imdb, tvdb, tvshowtitle, year):
try:
url = self.tvsearch_link % cleantitle.geturl(tvshowtitle)
r = urlparse.urljoin(self.base_link, url)
r = client.request(r, limit='1')
r = client.parseDOM(r, 'title')
if not r:
url = 'http://www.imdb.com/title/%s' % imdb
url = client.request(url, headers={'Accept-Language':'es-ES'})
url = client.parseDOM(url, 'title')[0]
url = re.sub('\((?:.+?|)\d{4}.+', '', url).strip()
url = cleantitle.normalize(url.encode("utf-8"))
url = self.tvsearch_link % cleantitle.geturl(url)
r = urlparse.urljoin(self.base_link, url)
r = client.request(r, limit='1')
r = client.parseDOM(r, 'title')
if not year in r[0]: raise Exception()
return url
except:
return示例5: tvshow
def tvshow(self, imdb, tvdb, tvshowtitle, localtvshowtitle, aliases, year):
try:
query = self.search_link % urllib.quote_plus(cleantitle.query(tvshowtitle))
# req page 3 times to workaround their BS random 404's
# responses (legit & BS 404s) are actually very fast: timeout prob not important
for i in range(4):
result = client.request(query, timeout=3)
if not result == None: break
t = [tvshowtitle] + source_utils.aliases_to_array(aliases)
t = [cleantitle.get(i) for i in set(t) if i]
result = re.compile('itemprop="url"\s+href="([^"]+).*?itemprop="name"\s+class="serie-title">([^<]+)', re.DOTALL).findall(result)
for i in result:
if cleantitle.get(cleantitle.normalize(i[1])) in t and year in i[1]: url = i[0]
url = url.encode('utf-8')
#log_utils.log('\n\n~~~ outgoing tvshow() url')
#log_utils.log(url)
# returned 'url' format like: /serie/x_files
return url
except:
return示例6: searchMovie
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
url = urlparse.urljoin(self.base_link, self.search_link % cleantitle.geturl(title))
r = client.request(url)
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title'))
results = [(i[0], i[1], re.findall('\((\d{4})', i[1])) for i in r]
try:
r = [(i[0], i[1], i[2][0]) for i in results if len(i[2]) > 0]
url = [i[0] for i in r if self.matchAlias(i[1], aliases) and (year == i[2])][0]
except:
url = None
pass
if (url == None):
url = [i[0] for i in results if self.matchAlias(i[1], aliases)][0]
url = urlparse.urljoin(self.base_link, '%s/watching.html' % url)
return url
except:
return示例7: getImdbTitle
def getImdbTitle(self, imdb):
try:
t = 'http://www.omdbapi.com/?i=%s' % imdb
t = client.request(t)
t = json.loads(t)
t = cleantitle.normalize(t['Title'])
return t
except:
return示例8: searchMovie
def searchMovie(self, title):
try:
title = cleantitle.normalize(title)
url = urlparse.urljoin(self.base_link, self.search_link_2 % urllib.quote_plus(cleantitle.getsearch(title)))
r = client.request(url, timeout='10')
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title'))
url = [i[0] for i in r if cleantitle.get(title) == cleantitle.get(i[1])][0]
return url
except:
return示例9: searchMovie
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
u = urlparse.urljoin(self.base_link, self.search_link)
p = urllib.urlencode({'keyword': title})
r = client.request(u, post=p, XHR=True)
r = json.loads(r)['content']
r = zip(client.parseDOM(r, 'a', ret='href', attrs={'class': 'ss-title'}), client.parseDOM(r, 'a', attrs={'class': 'ss-title'}))
url = [i[0] for i in r if self.matchAlias(i[1], aliases)][0]
return url
except:
return示例10: searchMovie
def searchMovie(self, title, headers):
try:
title = cleantitle.normalize(title)
url = urlparse.urljoin(self.base_link, self.search_link % cleantitle.geturl(title))
r = client.request(url, headers=headers, timeout='10')
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'h2'))
r = [i[0] for i in r if cleantitle.get(title) == cleantitle.get(i[1])][0]
url = urlparse.urljoin(self.base_link, '%s/watching.html' % r)
return url
except:
return示例11: getOriginalTitle
def getOriginalTitle(self, imdb):
try:
tmdb_link = base64.b64decode(
'aHR0cHM6Ly9hcGkudGhlbW92aWVkYi5vcmcvMy9maW5kLyVzP2FwaV9rZXk9MTBiYWIxZWZmNzZkM2NlM2EyMzQ5ZWIxMDQ4OTRhNmEmbGFuZ3VhZ2U9ZW4tVVMmZXh0ZXJuYWxfc291cmNlPWltZGJfaWQ=')
t = client.request(tmdb_link % imdb, timeout='10')
try: title = json.loads(t)['movie_results'][0]['original_title']
except: pass
try: title = json.loads(t)['tv_results'][0]['original_name']
except: pass
title = cleantitle.normalize(title)
return title
except:
return示例12: searchShow
def searchShow(self, title, season, aliases, headers):
try:
title = cleantitle.normalize(title)
u = urlparse.urljoin(self.base_link, self.search_link)
p = urllib.urlencode({'keyword': ('%s - Season %s' % (title, season))})
r = client.request(u, post=p, XHR=True)
r = json.loads(r)['content']
r = zip(client.parseDOM(r, 'a', ret='href', attrs={'class': 'ss-title'}), client.parseDOM(r, 'a', attrs={'class': 'ss-title'}))
r = [(i[0], i[1], re.findall('(.*?)\s+-\s+Season\s+(\d)', i[1])) for i in r]
r = [(i[0], i[1], i[2][0]) for i in r if len(i[2]) > 0]
url = [i[0] for i in r if self.matchAlias(i[2][0], aliases) and i[2][1] == season][0]
return url
except:
return示例13: searchMovie
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
cltitle = cleantitle.get(title)
url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(title)))
r = client.request(url, timeout='15')
r = [i[1] for i in re.findall(r'<li\s+class=["\']movie-item["\'].*?data-title=["\']([^"\']+)["\']><a\s+href=["\']([^"\']+)["\']',r, re.IGNORECASE)
if cleantitle.get(re.sub(r"\s*\d{4}","",i[0])) == cltitle]
if r == None: return
else: url = r[0]
return url
except:
return示例14: searchShow
def searchShow(self, title, season, aliases, headers):
try:
title = cleantitle.normalize(title)
search = '%s Season %01d' % (title, int(season))
url = urlparse.urljoin(self.base_link, self.search_link % urllib.quote_plus(cleantitle.getsearch(search)))
r = client.request(url, headers=headers, timeout='15')
r = client.parseDOM(r, 'div', attrs={'class': 'ml-item'})
r = zip(client.parseDOM(r, 'a', ret='href'), client.parseDOM(r, 'a', ret='title'))
r = [(i[0], i[1], re.findall('(.*?)\s+-\s+Season\s+(\d)', i[1])) for i in r]
r = [(i[0], i[1], i[2][0]) for i in r if len(i[2]) > 0]
url = [i[0] for i in r if self.matchAlias(i[2][0], aliases) and i[2][1] == season][0]
return url
except:
return示例15: searchMovie
def searchMovie(self, title, year, aliases, headers):
try:
title = cleantitle.normalize(title)
title = cleantitle.getsearch(title)
query = self.search_link % ('%s+%s' % (urllib.quote_plus(title), year))
query = urlparse.urljoin(self.base_link, query)
r = client.request(query, timeout='15', headers=headers, mobile=True)
match = re.compile('alias=(.+?)\'">(.+?)</a>').findall(r)
match = [(i[0], re.findall('(.+?) \((\d{4})', i[1])) for i in match]
match = [(i[0], i[1][0][0], i[1][0][1]) for i in match if len(i[1]) > 0]
r = [(i[0],i[1]) for i in match if self.matchAlias(i[1], aliases) and year == i[2]][0]
return r
except:
return