def crawDailyStockComments(link):
currentList = []
startContext = ZZStockNetSpiderUtils.returnStartContext(
link, '<div class="column-box">')
startContext = ZZStockNetSpiderUtils.filterContextByTarget(
startContext, '<ul>', '<li class="nobg">')
len = ZZStockNetSpiderUtils.findAllTarget(startContext, '<li>')
for i in range(len):
targetContext = ZZStockNetSpiderUtils.divisionTarget(
startContext, '<li>', '</li>')
startContext = targetContext['nextContext']
currentContext = targetContext['targetContext']
currentYear = str(time.strftime('%Y', time.localtime(
time.time()))) + '-'
pubDate = currentYear + ZZStockNetSpiderUtils.filterContextByTarget(
currentContext, '<span class="ctime">(', ')</span>')
title = ZZStockNetSpiderUtils.filterContextByTarget(
currentContext, '.html">', '</a>')
linkUrl = ZZStockNetSpiderUtils.removeSpecialCharacter(currentContext)
if linkUrl != '':
linkUrl = ZZStockNetSpiderUtils.filterContextByTarget(
linkUrl, '<ahref="', 'html">') + '.html'
linkUrl = link + linkUrl
#descriptContext = crawDailyStockDescriptContext(linkUrl)
currentList.append([
str(uuid.uuid1()), linkUrl, title, pubDate, '', 'STOCK',
'ZZNET'
])
#print linkUrl
return currentList
def crawDailyStockDescriptContext(linkUrl):
startContext = ZZStockNetSpiderUtils.returnStartContext(
linkUrl,
'<div class="Dtext z_content" id="ozoom1" style="zoom: 100%;">')
print startContext
filterContext = ZZStockNetSpiderUtils.filterContextByTarget(
startContext, '<p>', '</p>')
print filterContext
def crawDailyStockComments(link):
currentList = []
startContext = ZZStockNetSpiderUtils.returnStartContext(link,'<div class="column-box">')
startContext = ZZStockNetSpiderUtils.filterContextByTarget(startContext,'<ul>','<li class="nobg">')
len = ZZStockNetSpiderUtils.findAllTarget(startContext,'<li>')
for i in range(len):
targetContext = ZZStockNetSpiderUtils.divisionTarget(startContext,'<li>','</li>')
startContext = targetContext['nextContext']
currentContext = targetContext['targetContext']
currentYear = str(time.strftime('%Y',time.localtime(time.time())))+'-'
pubDate = currentYear+ZZStockNetSpiderUtils.filterContextByTarget(currentContext,'<span class="ctime">(',')</span>')
title = ZZStockNetSpiderUtils.filterContextByTarget(currentContext,'.html">','</a>')
linkUrl = ZZStockNetSpiderUtils.removeSpecialCharacter(currentContext)
if linkUrl !='':
linkUrl = ZZStockNetSpiderUtils.filterContextByTarget(linkUrl,'<ahref="','html">')+'.html'
linkUrl = link + linkUrl
#descriptContext = crawDailyStockDescriptContext(linkUrl)
currentList.append([str(uuid.uuid1()),linkUrl,title,pubDate,'','STOCK','ZZNET'])
#print linkUrl
return currentList
def crawDailyStockDescriptContext(linkUrl):
startContext = ZZStockNetSpiderUtils.returnStartContext(linkUrl,'<div class="Dtext z_content" id="ozoom1" style="zoom: 100%;">')
print startContext
filterContext = ZZStockNetSpiderUtils.filterContextByTarget(startContext,'<p>','</p>')
print filterContext