def listVideos(url):
content = getUrl(url)
contenttop = content[content.find('<div class="topStoryWrapper clear">'):]
contenttop = contenttop[:contenttop.find('<div class="subcategoryList clear">')]
titletop = contenttop[contenttop.find('<h2 class="topStoryTitle">'):]
match = re.compile('<a href="(.+?)" title="(.+?)"', re.DOTALL).findall(titletop)
url="http://"+language2+".euronews.com"+match[0][0]
title=match[0][1]
title=HTMLParser().unescape(title.decode('utf-8'))
title=title.encode('utf-8')
match = re.compile('src="(.+?)"', re.DOTALL).findall(titletop)
thumb = match[0]
match = re.compile('<p>(.+?)</p>', re.DOTALL).findall(titletop)
desc=match[0]
match = re.compile('([0-9]+/[0-9]+ [0-9]+:[0-9]+) CET', re.DOTALL).findall(contenttop)
datum= match[0]
debug("TITLE: " + title)
debug("URL: " + url)
addLink(datum +" - "+title, url, 'playVideo', thumb, desc)
spl = content.split('<li class="clearAfter fixedHeight">')
for i in range(1, len(spl), 1):
element=spl[i]
match = re.compile('([0-9]+/[0-9]+ [0-9]+:[0-9]+) CET', re.DOTALL).findall(element)
datum= match[0]
debug("++++++++ "+ datum)
sp2 = element.split('<a title="INSIDERS"')
for i2 in range(0, len(sp2), 1):
element=sp2[i2]
debug("---------")
debug(element)
debug("---------")
match = re.compile('href="([^"]+?)"[ ]+title="([^"]+?)"', re.DOTALL).findall(element)
if not match:
debug("Keine Url")
continue
url="http://"+language2+".euronews.com"+match[0][0]
title=match[0][1]
match = re.compile('src="(.+?)"', re.DOTALL).findall(element)
if match:
thumb = match[0]
else:
thump=""
match = re.compile('<p>(.+?)</p>', re.DOTALL).findall(element)
if match:
desc=match[0]
else :
desc=""
debug("URL :" + url)
title=HTMLParser().unescape(title.decode('utf-8'))
title=title.encode('utf-8')
addLink( datum +" - "+title, url, 'playVideo', thumb, desc)
xbmcplugin.endOfDirectory(pluginhandle)
if forceViewMode == "true":
xbmc.executebuiltin('Container.SetViewMode('+viewMode+')')
def _download_video_subtitles(video_id):
"""Download English subtitles from video and return name of the SRT file.
Args:
video_id (str): ID of the video of which subtitiles are downloaded.
Raises:
AttributeError: if English subtitles not found.
Returns:
str: name of the SRT file where subtitles are located.
"""
response = urllib2.urlopen(
'http://video.google.com/timedtext?lang=en&v={}'.format(video_id))
xml_text = response.read()
if not xml_text:
raise AttributeError('English subtitles not found')
# Replace all escaped characters with unicode.
xml_text = HTMLParser().unescape(xml_text.decode('utf-8'))
srt_text = xml2srt.convert(xml_text)
subtitles_filename = '{}.srt'.format(video_id)
with open(subtitles_filename, 'w') as outfile:
outfile.write(srt_text.encode('utf8'))
return subtitles_filename
def unescape(string):
unescaped_string = HTMLParser().unescape(string)
unescaped_string_type = type(unescaped_string)
if unescaped_string_type == str:
return unescaped_string.decode('utf-8')
else:
return unescaped_string
def decoder(val, encodings=ENCODINGS):
if not hasattr(val, 'decode'): return val
val = HTMLParser().unescape(val)
r = None
for e in encodings:
try:
r = val.decode(e)
break
except Exception, err:
# keep iterating til the correct encoding is discovered
continue
def decoder(val, encodings=ENCODINGS):
if not hasattr(val, 'decode'): return val
val = HTMLParser().unescape(val)
r = None
for e in encodings:
try:
r = val.decode(e)
break
except Exception, err:
# keep iterating til the correct encoding is discovered
continue
def getRegexParsed(
regexs,
url,
cookieJar=None,
forCookieJarOnly=False,
recursiveCall=False,
cachedPages={},
rawPost=False,
cookie_jar_file=None): # 0,1,2 = URL, regexOnly, CookieJarOnly
# cachedPages = {}
# print 'url',url
doRegexs = re.compile('\$doregex\[([^\]]*)\]').findall(url)
# print 'doRegexs',doRegexs,regexs
setresolved = True
for k in doRegexs:
if k in regexs:
# print 'processing ' ,k
m = regexs[k]
# print m
cookieJarParam = False
if 'cookiejar' in m: # so either create or reuse existing jar
# print 'cookiejar exists',m['cookiejar']
cookieJarParam = m['cookiejar']
if '$doregex' in cookieJarParam:
cookieJar = getRegexParsed(regexs, m['cookiejar'],
cookieJar, True, True,
cachedPages)
cookieJarParam = True
else:
cookieJarParam = True
# print 'm[cookiejar]',m['cookiejar'],cookieJar
if cookieJarParam:
if cookieJar is None:
# print 'create cookie jar'
cookie_jar_file = None
if 'open[' in m['cookiejar']:
cookie_jar_file = m['cookiejar'].split(
'open[')[1].split(']')[0]
# print 'cookieJar from file name',cookie_jar_file
cookieJar = getCookieJar(cookie_jar_file)
# print 'cookieJar from file',cookieJar
if cookie_jar_file:
saveCookieJar(cookieJar, cookie_jar_file)
# import cookielib
# cookieJar = cookielib.LWPCookieJar()
# print 'cookieJar new',cookieJar
elif 'save[' in m['cookiejar']:
cookie_jar_file = m['cookiejar'].split('save[')[1].split(
']')[0]
complete_path = os.path.join(profile, cookie_jar_file)
# print 'complete_path',complete_path
saveCookieJar(cookieJar, cookie_jar_file)
if m['page'] and '$doregex' in m['page']:
pg = getRegexParsed(regexs,
m['page'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if len(pg) == 0:
pg = 'http://regexfailed'
m['page'] = pg
if 'setcookie' in m and m['setcookie'] and '$doregex' in m[
'setcookie']:
m['setcookie'] = getRegexParsed(regexs,
m['setcookie'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if 'appendcookie' in m and m['appendcookie'] and '$doregex' in m[
'appendcookie']:
m['appendcookie'] = getRegexParsed(regexs,
m['appendcookie'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if 'post' in m and '$doregex' in m['post']:
m['post'] = getRegexParsed(regexs,
m['post'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
# print 'post is now',m['post']
if 'rawpost' in m and '$doregex' in m['rawpost']:
m['rawpost'] = getRegexParsed(regexs,
m['rawpost'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages,
rawPost=True)
# print 'rawpost is now',m['rawpost']
if 'rawpost' in m and '$epoctime$' in m['rawpost']:
m['rawpost'] = m['rawpost'].replace('$epoctime$',
getEpocTime())
if 'rawpost' in m and '$epoctime2$' in m['rawpost']:
m['rawpost'] = m['rawpost'].replace('$epoctime2$',
getEpocTime2())
link = ''
if m['page'] and m[
'page'] in cachedPages and not 'ignorecache' in m and forCookieJarOnly is False:
# print 'using cache page',m['page']
link = cachedPages[m['page']]
else:
if m['page'] and not m['page'] == '' and m['page'].startswith(
'http'):
if '$epoctime$' in m['page']:
m['page'] = m['page'].replace('$epoctime$',
getEpocTime())
if '$epoctime2$' in m['page']:
m['page'] = m['page'].replace('$epoctime2$',
getEpocTime2())
# print 'Ingoring Cache',m['page']
page_split = m['page'].split('|')
pageUrl = page_split[0]
header_in_page = None
if len(page_split) > 1:
header_in_page = page_split[1]
# if
# proxy = ProxyHandler({ ('https' ? proxytouse[:5]=="https":"http") : proxytouse})
# opener = build_opener(proxy)
# install_opener(opener)
# print 'getproxies',getproxies()
current_proxies = ProxyHandler(getproxies())
# print 'getting pageUrl',pageUrl
req = Request(pageUrl)
if 'proxy' in m:
proxytouse = m['proxy']
# print 'proxytouse',proxytouse
# getproxies= lambda: {}
if pageUrl[:5] == "https":
proxy = ProxyHandler({'https': proxytouse})
# req.set_proxy(proxytouse, 'https')
else:
proxy = ProxyHandler({'http': proxytouse})
# req.set_proxy(proxytouse, 'http')
opener = build_opener(proxy)
install_opener(opener)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:14.0) Gecko/20100101 Firefox/14.0.1'
)
proxytouse = None
if 'referer' in m:
req.add_header('Referer', m['referer'])
if 'accept' in m:
req.add_header('Accept', m['accept'])
if 'agent' in m:
req.add_header('User-agent', m['agent'])
if 'x-req' in m:
req.add_header('X-Requested-With', m['x-req'])
if 'x-addr' in m:
req.add_header('x-addr', m['x-addr'])
if 'x-forward' in m:
req.add_header('X-Forwarded-For', m['x-forward'])
if 'setcookie' in m:
# print 'adding cookie',m['setcookie']
req.add_header('Cookie', m['setcookie'])
if 'appendcookie' in m:
# print 'appending cookie to cookiejar',m['appendcookie']
cookiestoApend = m['appendcookie']
cookiestoApend = cookiestoApend.split(';')
for h in cookiestoApend:
n, v = h.split('=')
w, n = n.split(':')
ck = cookielib.Cookie(version=0,
name=n,
value=v,
port=None,
port_specified=False,
domain=w,
domain_specified=False,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=True,
comment=None,
comment_url=None,
rest={'HttpOnly': None},
rfc2109=False)
cookieJar.set_cookie(ck)
if 'origin' in m:
req.add_header('Origin', m['origin'])
if header_in_page:
header_in_page = header_in_page.split('&')
for h in header_in_page:
n, v = h.split('=')
req.add_header(n, v)
if cookieJar is not None:
# print 'cookieJarVal',cookieJar
cookie_handler = HTTPCookieProcessor(cookieJar)
opener = build_opener(cookie_handler,
HTTPBasicAuthHandler(),
HTTPHandler())
opener = install_opener(opener)
# print 'noredirect','noredirect' in m
if 'noredirect' in m:
opener = build_opener(cookie_handler,
NoRedirection,
HTTPBasicAuthHandler(),
HTTPHandler())
opener = install_opener(opener)
elif 'noredirect' in m:
opener = build_opener(NoRedirection,
HTTPBasicAuthHandler(),
HTTPHandler())
opener = install_opener(opener)
if 'connection' in m:
# print '..........................connection//////.',m['connection']
from keepalive import HTTPHandler
keepalive_handler = HTTPHandler()
opener = build_opener(keepalive_handler)
install_opener(opener)
# print 'after cookie jar'
post = None
if 'post' in m:
postData = m['post']
# if '$LiveStreamRecaptcha' in postData:
# (captcha_challenge,catpcha_word,idfield)=processRecaptcha(m['page'],cookieJar)
# if captcha_challenge:
# postData=postData.replace('$LiveStreamRecaptcha','manual_recaptcha_challenge_field:'+captcha_challenge+',recaptcha_response_field:'+catpcha_word+',id:'+idfield)
splitpost = postData.split(',')
post = {}
for p in splitpost:
n = p.split(':')[0]
v = p.split(':')[1]
post[n] = v
post = urlencode(post)
if 'rawpost' in m:
post = m['rawpost']
# if '$LiveStreamRecaptcha' in post:
# (captcha_challenge,catpcha_word,idfield)=processRecaptcha(m['page'],cookieJar)
# if captcha_challenge:
# post=post.replace('$LiveStreamRecaptcha','&manual_recaptcha_challenge_field='+captcha_challenge+'&recaptcha_response_field='+catpcha_word+'&id='+idfield)
link = ''
try:
if post:
response = urlopen(req, post)
else:
response = urlopen(req)
if response.info().get('Content-Encoding') == 'gzip':
from StringIO import StringIO
import gzip
buf = StringIO(response.read())
f = gzip.GzipFile(fileobj=buf)
link = f.read()
else:
link = response.read()
if 'proxy' in m and not current_proxies is None:
install_opener(build_opener(current_proxies))
link = javascriptUnEscape(link)
# print repr(link)
# print link This just print whole webpage in LOG
if 'includeheaders' in m:
# link+=str(response.headers.get('Set-Cookie'))
link += '$$HEADERS_START$$:'
for b in response.headers:
link += b + ':' + response.headers.get(
b) + '\n'
link += '$$HEADERS_END$$:'
# print link
response.close()
except:
pass
cachedPages[m['page']] = link
# print link
# print 'store link for',m['page'],forCookieJarOnly
if forCookieJarOnly:
return cookieJar # do nothing
elif m['page'] and not m['page'].startswith('http'):
if m['page'].startswith('$pyFunction:'):
val = doEval(m['page'].split('$pyFunction:')[1], '',
cookieJar, m)
if forCookieJarOnly:
return cookieJar # do nothing
link = val
link = javascriptUnEscape(link)
else:
link = m['page']
if '$doregex' in m['expres']:
m['expres'] = getRegexParsed(regexs,
m['expres'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if not m['expres'] == '':
# print 'doing it ',m['expres']
if '$LiveStreamCaptcha' in m['expres']:
val = askCaptcha(m, link, cookieJar)
# print 'url and val',url,val
url = url.replace("$doregex[" + k + "]", val)
elif m['expres'].startswith(
'$pyFunction:') or '#$pyFunction' in m['expres']:
# print 'expeeeeeeeeeeeeeeeeeee',m['expres']
val = ''
if m['expres'].startswith('$pyFunction:'):
val = doEval(m['expres'].split('$pyFunction:')[1],
link, cookieJar, m)
else:
val = doEvalFunction(m['expres'], link, cookieJar, m)
if 'ActivateWindow' in m['expres']: return
if forCookieJarOnly:
return cookieJar # do nothing
if 'listrepeat' in m:
listrepeat = m['listrepeat']
return listrepeat, eval(val), m, regexs, cookieJar
try:
url = url.replace(u"$doregex[" + k + "]", val)
except:
url = url.replace("$doregex[" + k + "]",
val.decode("utf-8"))
else:
if 'listrepeat' in m:
listrepeat = m['listrepeat']
ret = re.findall(m['expres'], link)
return listrepeat, ret, m, regexs
val = ''
if not link == '':
# print 'link',link
reg = re.compile(m['expres']).search(link)
try:
val = reg.group(1).strip()
except:
traceback.print_exc()
elif m['page'] == '' or m['page'] is None:
val = m['expres']
if rawPost:
# print 'rawpost'
val = quote_plus(val)
if 'htmlunescape' in m:
# val=unquote_plus(val)
try:
from HTMLParser import HTMLParser
except ImportError:
from html.parser import HTMLParser
val = HTMLParser().unescape(val)
try:
url = url.replace("$doregex[" + k + "]", val)
except:
url = url.replace("$doregex[" + k + "]",
val.decode("utf-8"))
# print 'ur',url
# return val
else:
url = url.replace("$doregex[" + k + "]", '')
if '$epoctime$' in url:
url = url.replace('$epoctime$', getEpocTime())
if '$epoctime2$' in url:
url = url.replace('$epoctime2$', getEpocTime2())
if '$GUID$' in url:
import uuid
url = url.replace('$GUID$', str(uuid.uuid1()).upper())
if '$get_cookies$' in url:
url = url.replace('$get_cookies$', getCookiesString(cookieJar))
if recursiveCall: return url
# print 'final url',repr(url)
if url == "":
return
else:
return url, setresolved
