def parseArticle(self, baseUrl, link):
data = self.readUrl(link)
searchItems = re.findall(
r'<article class="news-article">.*?<div class="article-info">.*?<div class="col-sm-3 col-xs-6">.*?<strong>EMITIRANO</strong>:<br>(.+?)</div>.*?</div>.*?<div id="jplayer_container" class="audio-player played repeat-on">.*?<div class="track-info">.*?<p class="track-title">(.+?)</p>.*?<div class="download-section">.*?<h4>Preuzmite datoteku</h4>.*?<a href="(.+?)" class="attachment-file">.*?<span class="file-size pull-right">(.+?)</span>.*?</a>.*?</div>.*?<blockquote>.*?<h3>.*?</h3>.*?<p>(.+?)</p>.*?</blockquote>.*?</article>',
data,
re.DOTALL,
)
if not searchItems:
return None
article = Article()
article.pubDate = searchItems[0][0].strip()
article.title = searchItems[0][1].strip()
article.link = baseUrl + searchItems[0][2].strip()
# article.size = searchItems[0][3].strip()
article.description = searchItems[0][4].strip()
return article
def createArticle(self, baseUrl, articleData):
data = self.readUrl(baseUrl + articleData[0])
chennelDatas = re.findall(
r'<div class="main-content">.*?<article class="article-content">.*?<div class="user-content">.*?<h1>(.*?)</h1>.*?</article>.*?<script type="text/javascript">.*?mp3: "(.+?)".*?</script>.*?</div>',
data, re.DOTALL)
article = Article()
article.title = chennelDatas[0][0]
article.link = chennelDatas[0][1]
article.pubDate = articleData[2]
article.description = ''
descriptionDatas = re.findall(r'<p class="description">(.+?)</p>', data, re.DOTALL)
if len(descriptionDatas) > 0:
article.description = descriptionDatas[0]
else:
descriptionDatas = re.findall(r'<div class="content">.*?<p>(.+?)</p>.*?</div>', data, re.DOTALL)
if len(descriptionDatas) > 0:
article.description = descriptionDatas[0]
return article
