def getPageCount(self):
searchUrl = "http://www.hkn24.com/news/articleList.html?page=1&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=&sc_edate=&sc_serial_number=&sc_word=" + self.query + "&sc_view_code=&view_type="
soup = Soup.phantomjs(searchUrl)
pageCount = int(
re.sub("\D", "",
soup.find('font', color='#333333').get_text()))
return math.floor(pageCount / 20)
def getPageCount(self):
searchUrl = "http://www.khanews.com/news/articleList.html?page=&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=2000.01.01&sc_edate=&sc_serial_number=&sc_word=" + self.query + "&view_type="
soup = Soup.phantomjs(searchUrl)
tbodys = soup.find("td", bgcolor="#FFFFFF")
pageCount = int(
re.sub("\D", "",
tbodys.find("font", color="#333333").get_text()))
return math.floor(pageCount / 20)
def getPageHrefs(self, count):
searchUrl = "http://www.hkn24.com/news/articleList.html?page=" + str(
count
) + "&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=&sc_edate=&sc_serial_number=&sc_word=" + self.query + "&sc_view_code=&view_type="
soup = Soup.phantomjs(searchUrl)
searchBox = soup.find_all('td', class_='ArtList_Title')
pageHrefs = [
"http://www.hkn24.com/news/" + x.a.get('href') for x in searchBox
]
return pageHrefs
def getPageHrefs(self, count):
searchUrl = "http://www.doctorsnews.co.kr/news/articleList.html?page=" + str(
count
) + "&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_add_section_code=&sc_add_sub_section_code=&sc_add_serial_code=&sc_area=A&sc_level=&sc_m_level=&sc_article_type=&sc_view_level=&sc_sdate=" + self.startDate + "&sc_edate=" + self.endDate + "&sc_serial_number=&sc_word=" + self.query + "&sc_word2=&sc_andor=OR&sc_order_by=I&view_type="
soupArticle = Soup.phantomjs(searchUrl)
articleHrefList = soupArticle.find_all("a", class_="news_list_title")
pageHrefs = [
"http://www.doctorsnews.co.kr/news/" + x.get('href')
for x in articleHrefList
]
return pageHrefs
def getPageHrefs(self, count):
searchUrl = "http://www.khanews.com/news/articleList.html?page=" + str(
count
) + "&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=2000.01.01&sc_edate=&sc_serial_number=&sc_word=" + self.query + "&view_type="
soup = Soup.phantomjs(searchUrl)
searchBox = soup.find("td",
bgcolor="#FFFFFF").find_all("font",
color="#001DD0")
pageHrefs = [
"http://www.khanews.com/news/" + x.parent.get('href')
for x in searchBox
]
return pageHrefs
def getPageCount(self):
searchUrl = "http://www.doctorsnews.co.kr/news/articleList.html?page=1&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_add_section_code=&sc_add_sub_section_code=&sc_add_serial_code=&sc_area=A&sc_level=&sc_m_level=&sc_article_type=&sc_view_level=&sc_sdate=" + self.startDate + "&sc_edate=" + self.endDate + "&sc_serial_number=&sc_word=" + self.query + "&sc_word2=&sc_andor=OR&sc_order_by=I&view_type="
soup = Soup.phantomjs(searchUrl)
articleCnt = soup.find("tr", height="35").td.get_text()
maxArticle = int(re.sub("\D", "", articleCnt))
return math.floor(int(maxArticle / 25))
def getPageHrefs(self, count):
searchUrl = "http://www.doctorstimes.com/news/articleList.html?page="+str(count)+"&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=&sc_edate=&sc_serial_number=&sc_word="+self.query+"&sc_word2=&sc_andor=&sc_order_by=E&view_type="
soup = Soup.phantomjs(searchUrl,'html.parser')
searchBox = soup.find_all('td',class_='list-titles list-pad-5')
pageHrefs = ["http://www.doctorstimes.com/news/"+x.a.get('href') for x in searchBox]
return pageHrefs
def getPageCount(self):
searchUrl = "http://www.doctorstimes.com/news/articleList.html?page=1&sc_section_code=&sc_sub_section_code=&sc_serial_code=&sc_area=A&sc_level=&sc_article_type=&sc_view_level=&sc_sdate=&sc_edate=&sc_serial_number=&sc_word="+self.query+"&sc_word2=&sc_andor=&sc_order_by=E&view_type="
soup = Soup.phantomjs(searchUrl)
pageCount = int(re.sub("\D","",soup.select("#article-list > tbody > tr > td > table > tbody > tr:nth-of-type(1) > td > table > tbody > tr > td:nth-of-type(1)")[0].get_text()))
return math.floor(pageCount/20)