Function Page_Info

NewsSpider/NewsSpider.py:18–21

Regex

(myPage)

            fp.write("%s\t\t%s\n" % (s[0].encode("utf8"), s[1].encode("utf8")))

def Page_Info(myPage):
    '''Regex'''
    mypage_Info = re.findall(r'<div class="titleBar" id=".*?"><h2>(.*?)</h2><div class="more"><a href="(.*?)">.*?</a></div></div>', myPage, re.S)
    return mypage_Info

def New_Page_Info(new_page):
    '''Regex(slowly) or Xpath(fast)'''