def _get_title(_url):
HEADER = {'Accept-Language':'en-US,en;q=0.5'}
request = Request(_url, headers=HEADER)
data = urlopen(request)
htree=etree.parse(data, hparser)
raw_title = htree.find(".//title").text
code = get_host_code(_url)
title = title_cleaners[code](raw_title)
title = re.sub('[\|\*\[\]\(\)~\\\]','',title)
return title
def _get_title(_url):
HEADER = {'Accept-Language': 'en-US,en;q=0.5'}
request = Request(_url, headers=HEADER)
data = urlopen(request)
htree = etree.parse(data, hparser)
raw_title = htree.find(".//title").text
code = get_host_code(_url)
title = title_cleaners[code](raw_title)
title = re.sub('[\|\*\[\]\(\)~\\\]', '', title)
return title
def get_video_links_from_html(text):
"""
Strips video link from a string in html format
by looking for the href attribute.
"""
# could also just use BeautifulSoup, but this regex works fine
link_pat = re.compile('href="(.*?)"')
links = link_pat.findall(text)
video_links = []
for l in links:
code = get_host_code(l)
if code:
clean = link_cleaners[code]
if clean:
link = clean(fix_html_entities(l))
if link:
video_links.append(link)
return video_links
def get_video_links_from_html(text):
"""
Strips video link from a string in html format
by looking for the href attribute.
"""
# could also just use BeautifulSoup, but this regex works fine
link_pat = re.compile('href="(.*?)"')
links = link_pat.findall(text)
video_links = []
for l in links:
code = get_host_code(l)
if code:
clean = link_cleaners[code]
if clean:
link = clean(fix_html_entities(l))
if link:
video_links.append(link)
return video_links
