Python urllib2.unquote方法代码示例

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def handle_starttag(self, tag, attrs):
        if tag == 'h3' and attrs == [('class', 'r')]:
            self.h3_flag = True

        if tag == 'a' and self.h3_flag:
            self.a_flag = True

        if tag == 'b' and self.a_flag:
            self.b_flag = True

        if self.a_flag:
            for (key, value) in attrs:
                if key == 'href':
                    if value.startswith("/url?"):
                        m = match('/url\?(url|q)=(.+?)&', value)
                        if m and len(m.groups()) == 2:
                            href = urllib2.unquote(m.group(2))
                            self.link = href
                    else:
                        self.link = value 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def get_video_url(page_url, premium = False, user="", password="", video_password="", page_data=""):

    logger.info("tvalacarta.servers.vuittv get_video_url page_url="+page_url)

    data = scrapertools.cache_page(page_url)
    url2 = scrapertools.find_single_match(data,'<iframe width="[^"]+" height="[^"]+" scrolling="[^"]+" data-src="(http://www-arucitys-com.filesusr.com[^"]+)"')
    logger.info("url2="+url2)

    data = scrapertools.cache_page(url2)
    media_url = scrapertools.find_single_match(data,'"sourceURL"\:"([^"]+)"')
    logger.info("media_url="+media_url)

    media_url = urllib2.unquote(media_url)
    logger.info("media_url="+media_url)
    
    video_urls = []
    video_urls.append([ scrapertools.get_filename_from_url(media_url)[-4:], media_url ])

    return video_urls

# Encuentra vídeos del servidor en el texto pasado 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def cloudspace():
    '''
    show xunlei cloud space content
    '''
    dhurl = '%s/%s/?type=all&order=create&t=%s' % (
        cloudurlpre,
        'req_history_play_list/req_num/200/req_offset/0',
        cachetime)
    rsp = xl.urlopen(dhurl)
    vods = json.loads(rsp)['resp']['history_play_list']

    menu = [
        {'label': urllib2.unquote(v['file_name'].encode('utf-8')),
         'path': plugin.url_for('playcloudvideo',
                                vinfo=str((v['src_url'], v['gcid'],
                                           v['cid'], v['file_name'])))}
        for v in vods if 'src_url' in v]
    return menu 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def _cleanstr(self, str):
        str = str.strip()
        if str.find("function") == 0:
            pattern = (r"=\"([^\"]+).*}\s*\((\d+)\)")
            args = re.search(pattern, str, re.DOTALL)
            if args:
                a = args.groups()

                def openload_re(match):
                    c = match.group(0)
                    b = ord(c) + int(a[1])
                    return chr(b if (90 if c <= "Z" else 122) >= b else b - 26)

                str = re.sub(r"[a-zA-Z]", openload_re, a[0]);
                str = urllib2.unquote(str)

        elif str.find("decodeURIComponent") == 0:
            str = re.sub(r"(^decodeURIComponent\s*\(\s*('|\"))|(('|\")\s*\)$)", "", str);
            str = urllib2.unquote(str)
        elif str.find("\"") == 0:
            str = re.sub(r"(^\")|(\"$)|(\".*?\")", "", str);
        elif str.find("'") == 0:
            str = re.sub(r"(^')|('$)|('.*?')", "", str);

        return str 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def obfuscation_unescape(page):
    soup = BeautifulSoup(page, "lxml")
    for scr in soup(["script"]):
        if re.search('unescape', str(scr), re.IGNORECASE):
            encoded = re.search("(?:%[0-9A-F][0-9A-F][^\"]+)", str(scr), re.IGNORECASE)
            decoded_content = urllib2.unquote(encoded.group(0))
            scr.replace_with(decoded_content)
    decoded_page = soup.decode(formatter=None)   
    tmp_file = "/tmp/tmp.html"
    with open (tmp_file, "wb") as temp_f:
        temp_f.write(decoded_page)
        temp_f.close()
    try:
        response = br.open('file://' + tmp_file)
        global using_selenium
        using_selenium = True
        return response
    except Exception:
        return False 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def log_url(log, message, url, level = logging.DEBUG ):
    """Nicely logs the given url.
    
    Print out the url with the first part (protocol, host, port, authority,
    user info, path, ref) and in sequence all the query parameters.
    
    log: the log into which write the message
    message: a message to print before the url
    url: the url to log
    level: (optional) the log level to use"""
    
    urls = url.split('?')
    log.log( level, message + unquote(urls[0]) )
    if len(urls) > 1:
        for a in sorted(urls[1].split('&')):
            param = a.split('=')
            if( len(param) < 2 ):
              param.append('')
            log.log( level, ' . %s = %s', unquote(param[0]), unquote(param[1]) ) 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def build_httmock_functions(mock_response_dir):
    print 'building mock functions'
    functions = []
    for filename in listdir(mock_response_dir):
        filepath = join(mock_response_dir,filename)
        if isfile(filepath):
            method = None
            for _method in ('GET', 'POST', 'PUT', 'DELETE', 'PATCH'):
                if filename.startswith(_method):
                    filename = filename[len(_method):]
                    method = _method

            url = urllib2.unquote(filename)

            parts = urlparse(url)
            params = {}
            if parts.query:
                print parts.query
                params = dict(parse_qsl(parts.query))
                print params
            with open(filepath) as f:
                content = f.read()
                functions.append(build_httmock_function(
                    parts.scheme, parts.netloc, parts.path, content, params=params, method=method))
    return functions 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def __extract_video(self, item):
        sources = []
        for e in item:
            if isinstance(e, dict):
                for key in e:
                    for item2 in e[key]:
                        if isinstance(item2, list):
                            for item3 in item2:
                                if isinstance(item3, list):
                                    for item4 in item3:
                                        if isinstance(item4, unicode):
                                            item4 = item4.encode('utf-8')
                                            
                                        if isinstance(item4, basestring):
                                            item4 = urllib2.unquote(item4).decode('unicode_escape')
                                            for match in re.finditer('url=(?P<link>[^&]+).*?&itag=(?P<itag>[^&]+)', item4):
                                                link = match.group('link')
                                                itag = match.group('itag')
                                                quality = self.itag_map.get(itag, 'Unknown Quality [%s]' % itag)
                                                sources.append((quality, link))
                                            if sources:
                                                return sources
        return sources 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def _parse_gdocs(self, html):
        urls = []
        for match in re.finditer('\[\s*"([^"]+)"\s*,\s*"([^"]+)"\s*\]', html):
            key, value = match.groups()
            if key == 'fmt_stream_map':
                items = value.split(',')
                for item in items:
                    _source_itag, source_url = item.split('|')
                    if isinstance(source_url, unicode):
                        source_url = source_url.encode('utf-8')
                        
                    source_url = source_url.decode('unicode_escape')
                    quality = self.itag_map.get(_source_itag, 'Unknown Quality [%s]' % _source_itag)
                    source_url = urllib2.unquote(source_url)
                    urls.append((quality, source_url))
                return urls

        return urls 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def myviru(self,url,referer,options):
        COOKIEFILE = ptv.getAddonInfo('path') + os.path.sep + "cookies" + os.path.sep + "myviru.cookie"
        query_data = { 'url': url, 'use_host': False, 'use_header': False, 'use_cookie': True, 'cookiefile': COOKIEFILE, 'save_cookie': True, 'use_post': False, 'return_data': True }
        link = self.cm.getURLRequestData(query_data)
        linkvideo = ''
        match2= re.compile("dataUrl:'(.*?)',").findall(link)

        if len(match2)>0:
            mylink = 'http://myvi.ru'+urllib2.unquote(match2[0])
            query_data = { 'url': mylink, 'use_host': False, 'use_header': False, 'use_cookie': True, 'cookiefile': COOKIEFILE, 'load_cookie': True, 'use_post': False, 'return_data': True }
            result = self.cm.getURLRequestData(query_data)
            result = urllib.unquote(result).replace('\\/', '/').replace('\n', '').replace('\'', '"').replace(' ', '')
            match3= re.compile('"video":\[{"url":"([^"]+)"}\]').findall(result)
            if len(match3)>0:
                mycook = self.cm.getCookieItem(COOKIEFILE,'UniversalUserID')
                mycook = urllib.urlencode({'UniversalUserID':mycook})
                return '%s|Cookie=%s' % (match3[0], mycook)
        return linkvideo 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def parseucaster(self, url, referer,options):
        print ("a", url, referer,options)
        req = urllib2.Request(url)
        req.add_header('Referer', 'http://' + referer)
        req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:20.0) Gecko/20100101 Firefox/20.0')
        response = urllib2.urlopen(req)
        link = response.read()
        response.close()
        match = re.search('"file":      "(.*?)"', link)
        print ("ZZZZzzzz", link)

        if match:
            link = urllib.unquote(match.group(
                1)) + ' pageUrl=http://aliez.tv/live/mlb/ swfUrl=http://player.longtailvideo.com/player.swf app=aliezlive-live live=true tcUrl=rtmp://play.aliez.com/aliezlive-live'
            return link
        else:
            return False 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def parseraliez(self, url, referer,options):
        req = urllib2.Request(url)
        req.add_header('Referer', referer)
        req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:20.0) Gecko/20100101 Firefox/20.0')
        response = urllib2.urlopen(req)
        link = response.read()
        response.close()
        match = re.search('"file":(.*?)"(.*?)"', link)
        print ("ZZZZzzzz", match, link)
        print match.group(2)
        if match:
            link = urllib.unquote(match.group(
                2)) + ' pageUrl=http://aliez.tv/live/mlb/ swfUrl=http://player.longtailvideo.com/player.swf app=aliezlive-live live=true tcUrl=rtmp://play.aliez.com/aliezlive-live'
            return link
        else:
            return False 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def parserputlive(self, url, referer,options):
        print ("a", url, referer,options)
        req = urllib2.Request(url)
        req.add_header('Referer', 'http://' + referer)
        req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:20.0) Gecko/20100101 Firefox/20.0')
        response = urllib2.urlopen(req)
        link = response.read()
        response.close()
        print ("Link", link)
        match = re.compile('html\(unescape\("(.*?)"\)\);').findall(link)
        if len(match) > 0:
            print urllib.unquote(match[0])
            match1 = re.compile('src="(.*?)"').findall(urllib.unquote(match[0]))
            match2 = re.compile('streamer=(.*?)&').findall(urllib.unquote(match[0]))
            match3 = re.compile('file=(.*?)&').findall(urllib.unquote(match[0]))
            print ("Link", match1)
            print ("Link", match2)
            print ("Link", match3)
            return match2[0] + match3[0] + ' pageUrl=' + match1[0] + ' swfUrl=' + match1[0]
            #parsertopupload 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def myviru(self,url,referer,options):
        COOKIEFILE = self.cookieFileName('myviru')
        query_data = { 'url': url, 'use_host': False, 'use_header': False, 'use_cookie': True, 'cookiefile': COOKIEFILE, 'save_cookie': True, 'use_post': False, 'return_data': True }
        link = self.cm.getURLRequestData(query_data)
        self.log.info('aaa %s' % link)
        linkvideo = ''
        match2= re.compile("dataUrl:'(.*?)',").findall(link)

        if len(match2)>0:
            mylink = 'http://myvi.ru'+urllib2.unquote(match2[0])
            query_data = { 'url': mylink, 'use_host': False, 'use_header': False, 'use_cookie': True, 'cookiefile': COOKIEFILE, 'save_cookie': True, 'load_cookie': True, 'use_post': False, 'return_data': True }
            result = self.cm.getURLRequestData(query_data)

            result = urllib.unquote(result).replace('\\/', '/').replace('\n', '').replace('\'', '"').replace(' ', '')
            match3= re.compile('"video":\[{"url":"([^"]+)"}\]').findall(result)
            if len(match3)>0:
                self.log.info('aaa %s' % match3)

                mycook = self.cm.getCookieItem(COOKIEFILE,'UniversalUserID')
                mycook = urllib.urlencode({'UniversalUserID':mycook})
                self.log.info('aaa %s' % mycook)

                return '%s|Cookie=%s' % (match3[0], mycook)
        return linkvideo 

# 需要导入模块: import urllib2 [as 别名]
# 或者: from urllib2 import unquote [as 别名]
def parserVIDZER(self,url,referer, options):
        query_data = { 'url': url, 'use_host': False, 'use_cookie': False, 'use_post': False, 'return_data': True }
        link = self.cm.getURLRequestData(query_data)

        match = re.search('href="(http[^"]+?getlink[^"]+?)"', link)
        if match:
            url = urllib.unquote( match.group(1) )
            return url


        r = re.search('value="(.+?)" name="fuck_you"', link)
        r2 = re.search('name="confirm" type="submit" value="(.+?)"', link)
        r3 = re.search('<a href="/file/([^"]+?)" target', link)
        if r:
            query_data = { 'url': 'http://www.vidzer.net/e/'+r3.group(1)+'?w=631&h=425', 'use_host': False, 'use_cookie': False, 'use_post': True, 'return_data': True }
            postdata = {'confirm' : r2.group(1), 'fuck_you' : r.group(1)}
            link = self.cm.getURLRequestData(query_data, postdata)
            match = re.search("url: '([^']+?)'", link)
            if match:
                url = match.group(1) #+ '|Referer=http://www.vidzer.net/media/flowplayer/flowplayer.commercial-3.2.18.swf'
                return url
            else:
                return ''
        else:
            return ''