Example #1
0
def crawl():
    return basic.list_rss_crawl(url='http://www.huxiu.com/rss/0.xml',
                                title_select='h1.t-h1',
                                body_select='.article-content-wrap',
                                remove_tags=[])
Example #2
0
def crawl():
    return basic.list_rss_crawl(url='http://news.csdn.net/rss_news.html',
                                title_select='.detail h1.title',
                                body_select='.detail .news_content',
                                remove_tags=[])
Example #3
0
def crawl():
    return basic.list_rss_crawl(url='http://www.waerfa.com/feed', title_select='h1.article-title a', body_select='article.article-content', remove_tags=['div'])
Example #4
0
def crawl():
    return basic.list_rss_crawl(url='http://www.linuxidc.com/rssFeed.aspx', title_select='h1.aTitle', body_select='#content', remove_tags=[])
Example #5
0
def crawl():
    return basic.list_rss_crawl(url='http://www.jdon.com/rss', title_select='.post_warp .post_titlename h3 span', body_select='h1.tpc_content')
Example #6
0
def crawl():
    return basic.list_rss_crawl(url='http://www.iamue.com/feed',
                                title_select='h1.post-title',
                                body_select='section.article-content',
                                remove_tags=['div'])
Example #7
0
def crawl():
    return basic.list_rss_crawl(url='http://blog.netsh.org/feed', title_select='a.titlelink', body_select='#post-text', remove_tags=['div']

if __name__ == "__main__":
    crawl()
Example #8
0
def crawl():
    return basic.list_rss_crawl(url='http://www.yicai.com/rss/keji.xml',
                                title_select='.news h1',
                                body_select='.news .text',
                                remove_tags=[])
Example #9
0
def crawl():
    return basic.list_rss_crawl(url='http://www.digitaling.com/rss',
                                title_select='.article_title h2',
                                body_select='.article_con',
                                remove_tags=[])
    return basic.std_rss_crawl()
Example #10
0
def crawl():
    return basic.list_rss_crawl(url='http://rss.cnbeta.com/rss',
                                title_select='h2#news_title',
                                body_select='section.article_content',
                                remove_tags=[])
Example #11
0
def crawl():
    return basic.list_rss_crawl(url="http://tgideas.qq.com/rss.xml",
                                title_select="header.hd h2.tit",
                                body_select="section.bd",
                                remove_tags=[])
Example #12
0
def crawl():
    return basic.list_rss_crawl(url='http://88250.b3log.org/blog-articles-rss.do', title_select='title', body_select='section.article-body', remove_tags=[])
Example #13
0
def crawl():
    return basic.list_rss_crawl('http://www.idcps.com/rss', '.main h1',
                                '.main .content')