def getDetailPage(self):
content=FileUtil.readlines(self.saveFile)
for s in content:
title=s.split('|')[0] #标题
url=s.split('|')[1] #url
print url
page = HttpUtil.getPage(url);
arr = HtmlUtil.select_all(page, '.newText .Info span')
date=''
source=''
#获取时间/来源
for k in arr:
if k is not None:
if "年" in str(k):
date=str(k);
if "来源" in str(k):
source=str(k);
content_review = HtmlUtil.select_v(page, '#ContentBody .c_review')
if content_review is None:
content_review=''
arr = HtmlUtil.select_text(page, '#ContentBody p')
#记录到文件
newFile="data/finance"+url.split(',')[1][:-6]+".txt"
FileUtil.put(newFile, '')
FileUtil.appendline(newFile, title+"\n")
FileUtil.appendline(newFile, url)
FileUtil.appendline(newFile, date+"\n")
FileUtil.appendline(newFile, source+"\n")
FileUtil.appendline(newFile, content_review+"\n")
for k in arr:
try:
FileUtil.appendline(newFile, str(k))
except:
continue;
def getDetailPage(self):
srcFile=TimeUtil.prefix()+".txt"
content=FileUtil.readlines(srcFile)
for str in content:
url=str.split('|')[1]
print url
