Python utils.cleantext函数代码示例

def WXFList(url, page=1, onelist=None):
    if onelist:
        url = url.replace('/page/1/','/page/'+str(page)+'/')
    sort = getWXFSortMethod()
    if re.search('\?', url, re.DOTALL | re.IGNORECASE):
        url = url + '&filtre=' + sort + '&display=extract'
    else:
        url = url + '?filtre=' + sort + '&display=extract'
    try:
        listhtml = utils.getHtml(url, '')
    except Exception as e:
        return None
#    match = re.compile('src="([^"]+)" class="attachment-thumb_site.*?<a href="([^"]+)" title="([^"]+)".*?<p>([^<]+)</p>', re.DOTALL | re.IGNORECASE).findall(listhtml)
    match = re.compile('<article id=.*?<a href="([^"]+)" title="([^"]+)".*?<img data-src="([^"]+)" alt="([^"]+)"', re.DOTALL | re.IGNORECASE).findall(listhtml) # Current as of 19.02.23
#    for img, videopage, name, desc in match:
    for videopage, name, img, desc in match:      # Current as of 19.02.23
        name = utils.cleantext(name)
        desc = utils.cleantext(desc)
        utils.addDownLink(name, videopage, 13, img, desc)
    if not onelist:
        if re.search('<link rel="next"', listhtml, re.DOTALL | re.IGNORECASE):
            npage = page + 1
            url = url.replace('/page/' + str(page) + '/', '/page/' + str(npage) + '/')
            utils.addDir('Next Page ('+str(npage)+')', url, 11, '', npage)
        xbmcplugin.endOfDirectory(utils.addon_handle)

def Cat(url):
    listhtml = utils.getHtml(url, '')
    match = re.compile('<a class="item" href="([^"]+)" title="([^"]+)".*?data-original="([^"]+)".*?videos">([^<]+)<', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, name, img, videos in match:
        name = utils.cleantext(name) + " [COLOR deeppink]" + videos + "[/COLOR]"
        utils.addDir(name, catpage, 361, img, '')
    xbmcplugin.endOfDirectory(utils.addon_handle)

def v7_list(url, page=None, search=None):
    orig_url = str(url)
    if page:
        page_end = 'page/' + str(page) + '/' if url.endswith('/') else '/page/' + str(page) + '/'
        url += page_end
    else:
        page = 1
    sort = '?orderby=date' if url.endswith('/') else '/?orderby=date'
    url += sort
    url = url + search if search else url
    try:
        listhtml = utils.getHtml(url)
    except Exception as e:
        return None
    match = re.compile('''class='thumb-wrapp'.*?href='([^']+)'.*?"([^"]+)".*?class='vl'(.*?)class="duration">(.*?)</div>.*?class='hp'[^>]+>([^<]+)<''', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for videopage, img, hd, duration, name in match:
        hd = ' [COLOR orange]HD[/COLOR] ' if 'HD' in hd else ' '
        name = utils.cleantext(name) + hd + duration.strip()
        utils.addDownLink(name, videopage, 642, img, '')
    pages_html = re.compile('<div class="buttons">(.*?)</div', re.DOTALL | re.IGNORECASE).findall(listhtml)[0]
    pages = re.compile('<a[^>]+>(.*?)</a', re.DOTALL | re.IGNORECASE).findall(pages_html)
    pages = [int(p.replace('&nbsp;', '').replace('...', '').strip()) for p in pages]
    max_page = max(pages)
    if page < max_page:
        utils.addDir('Next Page (' + str(page + 1) + ')' , orig_url, 641, '', page + 1, search)
    xbmcplugin.endOfDirectory(utils.addon_handle)

def List(url):
    try:
        listhtml = utils.getHtml(url, '')
    except:
        
        return None
    match = re.compile('thumb-main-titre"><a href="..([^"]+)".*?title="([^"]+)".*?src="([^"]+)".*?<div class="thumb-info">(.*?)time">([^<]+)<', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for videourl, name, img, hd, duration in match:
        name = utils.cleantext(name)
        if hd.find('hd') > 0:
            if hd.find('full') > 0:
                hd = " [COLOR yellow]FULLHD[/COLOR] "
            else:
                hd = " [COLOR orange]HD[/COLOR] "
        else:
            hd = " "
        videopage = "http://www.absoluporn.com" + videourl
        videopage = videopage.replace(" ","%20")
        name = name + hd + "[COLOR deeppink]" + duration + "[/COLOR]"
        utils.addDownLink(name, videopage, 302, img, '')
    try:
        nextp=re.compile(r'<span class="text16">\d+</span> <a href="..([^"]+)"').findall(listhtml)[0]
        nextp = nextp.replace(" ","%20")
        utils.addDir('Next Page', 'http://www.absoluporn.com' + nextp, 301,'')
    except: pass    
    xbmcplugin.endOfDirectory(utils.addon_handle)

def pornvibe_cat(url):
	listhtml = utils.getHtml(url)
	match = re.compile('''<img src="([^"]+)" alt="([^"]+)">.+?href="([^"]+)".*?<p>([^&]+)&''', re.DOTALL | re.IGNORECASE).findall(listhtml)
	for img, name, catpage, count in sorted(match, key=lambda x: x[1].strip().lower()):
		name = utils.cleantext(name.strip()) + " [COLOR deeppink]" + count.strip() + " videos[/COLOR]"
		utils.addDir(name, catpage, 681, img, 1)
	xbmcplugin.endOfDirectory(utils.addon_handle)

def pl_cat(url):
    listhtml = utils.getHtml(url, 'https://porns.land/')
    match = re.compile('<div class="category".*?href="([^"]+)".*?data-original="([^"]+)".*?alt="([^"]+)"', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, img, name in match:
        name = utils.cleantext(name)
        utils.addDir(name, catpage, 621, img, 1)
    xbmcplugin.endOfDirectory(utils.addon_handle)

def datoporn_cat(url):
    listhtml = utils.getHtml(url)
    match = re.compile('''class="vid_block".*?href="([^"]+)".*?url[(]([^)]+)[)].*?<span>([^<]+)</span>.*?<b>([^<]+)</b''', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, img, count, name in sorted(match, key=lambda x: x[3].strip().lower()):
        name = utils.cleantext(name.strip()) + " [COLOR deeppink]" + count.strip() + "[/COLOR]"
        utils.addDir(name, catpage, 671, img, 1)
    xbmcplugin.endOfDirectory(utils.addon_handle)

def PTList(url, page=1, onelist=None):
    if onelist:
        url = url.replace('page=1','page='+str(page))
    try:
        listhtml = utils.getHtml(url, '')
    except:
        utils.notify('Oh oh','It looks like this website is down.')
        return None
    match = re.compile(r'<div class="(?:visible-xs|thumb-overlay)+">\s+<img src=.*?data-original="([^"]+)" title="([^"]+)"[^>]+>(.*?)duration">[^\d]+([^\t\n\r]+)', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for img, name, hd, duration in match:
        name = utils.cleantext(name)
        if hd.find('HD') > 0:
            hd = " [COLOR orange]HD[/COLOR] "
        else:
            hd = " "
        urlid = re.search(r"(\d{2,})", img, re.DOTALL | re.IGNORECASE).group()
        videopage = "http://www.porntrex.com/media/nuevo/config.php?key=" + urlid + "-1-1"
        name = name + hd + "[COLOR deeppink]" + duration + "[/COLOR]"
        utils.addDownLink(name, videopage, 52, img, '')
    if not onelist:
        if re.search('class="prevnext">Next', listhtml, re.DOTALL | re.IGNORECASE):
            npage = page + 1        
            url = url.replace('page='+str(page),'page='+str(npage))
            utils.addDir('Next Page ('+str(npage)+')', url, 51, '', npage)
        xbmcplugin.endOfDirectory(utils.addon_handle)

def Cat(url):
    listhtml = utils.getHtml(url, "")
    match = re.compile('<li><a href="([^"]+)" rel="tag">([^<]+)<', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, name in match:
        name = utils.cleantext(name)
        utils.addDir(name, catpage, 371, "", "")
    xbmcplugin.endOfDirectory(utils.addon_handle)

def v7_cat(url):
    listhtml = utils.getHtml(url, 'http://www.vidz7.com/')
    match = re.compile('li><a href="([^"]+)">(.*?)</a><span>([^<]+)<', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, name, nr in match:
        name = utils.cleantext(name) + ' [COLOR orange]' + nr.strip() + '[/COLOR]'
        utils.addDir(name, catpage, 641, '', 1)
    xbmcplugin.endOfDirectory(utils.addon_handle)

def Cat(url):
	listhtml = utils.getHtml3(url)
	match = re.compile('<a class="list-item__link" href="([^"]+)" title="([^"]+)".*?class="list-item__info">([^<]+)', re.DOTALL | re.IGNORECASE).findall(listhtml)
	for catpage, name, videos in match:
		videos=videos.replace(' ','')
		name = utils.cleantext(name) + " [COLOR deeppink]" + videos + "[/COLOR]"		
		utils.addDir(name, catpage, 361)
	xbmcplugin.endOfDirectory(utils.addon_handle)

def Categories(url):
    listhtml = utils.getHtml(url, '')
    match = re.compile(r'<li>\s+<a href="([^"]+)"[^<]+<[^<]+<img.*?src="([^"]+)".*?title">([^<]+)<', re.DOTALL | re.IGNORECASE).findall(listhtml)
    for catpage, img, name in match:
        name = utils.cleantext(name)
        catpage = catpage + '?sortby=post_date'
        utils.addDir(name, catpage, 341, img, '')
    xbmcplugin.endOfDirectory(utils.addon_handle)

def Cat(url):
    listhtml = utils.getHtml(url, '')
    match0 = re.compile('<h2>Categories(.+?)<tr id="myRow">', re.DOTALL | re.IGNORECASE).findall(listhtml)[0]	
    match = re.compile('<a href="(.+?)"\s+title=".+?">(.+?)<', re.DOTALL | re.IGNORECASE).findall(match0)
    for catpage, name in match:
        name = utils.cleantext(name)
        utils.addDir(name, catpage, 371, '', '')
    xbmcplugin.endOfDirectory(utils.addon_handle)

def Categories(url):
    listhtml = utils.getHtml(url, "")
    match = re.compile(
        '<a href="(.+?)" title=".+?">\n.+?<div class="thumb">\n.+?<img class="thumb" src="(.+?)" alt="(.+?)"/>'
    ).findall(listhtml)
    for catpage, img, name in match:
        name = utils.cleantext(name)
        utils.addDir(name, catpage, 341, img, "")
    xbmcplugin.endOfDirectory(utils.addon_handle)

def ChannelList(url):
    listhtml = utils.getHtml(url, '')
    match = re.compile('<a href="([^"]+)" class="thumb" data-rt=".+?">.+?<img  width="220" height="165" src="([^"]+)" alt="([^"]+)"', re.DOTALL).findall(listhtml)
    for videopage, img, name in match:
        name = utils.cleantext(name)
        utils.addDownLink(name, 'http://www.hclips.com' + videopage, 382, img, '')
    try:
        nextp=re.compile('<li class="next">.+?<a href="([^"]+)".*?>Next</a>', re.DOTALL | re.IGNORECASE).findall(listhtml)
        utils.addDir('Next Page', 'http://www.hclips.com' + nextp[0], 386,'')
    except: pass
    xbmcplugin.endOfDirectory(utils.addon_handle)