def crawMorningForexDailyNews(linkUrl): currentList = [] startContext = FXNewsForexNetSpiderUtils.returnStartContext(linkUrl,'<div class="yjl_fx168_news_listBox">') startContext = FXNewsForexNetSpiderUtils.filterContextByTarget(startContext,'<ul>','</ul>') len = FXNewsForexNetSpiderUtils.findAllTarget(startContext,'<li>') for i in range(len): targetContext = FXNewsForexNetSpiderUtils.divisionTarget(startContext,'<li>','</li>') startContext = targetContext['nextContext'] currentContext = targetContext['targetContext'] pubDate = FXNewsForexNetSpiderUtils.filterContextByTarget(currentContext,'<h5>','</h5>') currentContext = FXNewsForexNetSpiderUtils.removeSpecialCharacter(currentContext) currentContext = FXNewsForexNetSpiderUtils.filterAfterContext(currentContext,'<divclass="yjl_fx168_news_listPhoto">') linkUrl = FXNewsForexNetSpiderUtils.filterContextByTarget(currentContext,'href="','"title=') title = FXNewsForexNetSpiderUtils.filterContextByTarget(currentContext,'title="','><imglazy-src') imageUrl = FXNewsForexNetSpiderUtils.filterContextByTarget(currentContext,'imglazy-src="','"width=') descriptContext = FXNewsForexNetSpiderUtils.filterContextByTarget(currentContext,'<pclass="del">','</div></li>') currentTime = time.strftime("%Y-%m-%d",time.localtime()) if pubDate[:10]!=currentTime: break currentList.append([str(uuid.uuid1()),linkUrl,imageUrl,title,pubDate,descriptContext,'FOREX','FXNET']) return currentList