def getPageHrefs(self, count):
searchUrl = "http://www.medipana.com/news/news_list_new.asp?Page=" + str(count) + "&MainKind=A&NewsKind=106&vCount=20&vKind=1&sID=&sWord=" + self.query + "&sDate="
soup = Soup.requests(searchUrl, parser="html.parser")
searchBox = soup.find_all('a', class_='import_middle_title1')
regex = re.compile("&sWord=(.*)")
pageHrefs = ["http://www.medipana.com/" + regex.sub("", x.get('href')[2:]) for x in searchBox]
return pageHrefs
def getPage(self, url):
soup = Soup.requests(url)
articleID = re.sub("\D","",url)
articleTitle = soup.find('div',class_='art_top').h2.get_text().strip()
articleDate = re.sub("\D","",soup.find('ul',class_='art_info').contents[3].get_text())[:8]
articleTxt = soup.find('div',id='news_body_area').get_text(separator="\n").strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPageHrefs(self, count):
# 동아일보만 검색되게??? 나머지는???
searchUrl="http://news.donga.com/search?p="+str(count)+"&query="+self.query+"&check_news=1&more=1&sorting=1&search_date=1&v1="+self.startDate+"&v2="+self.endDate+"&range=1"
soup = Soup.requests(searchUrl)
searchBox = soup.find_all("div", class_="searchList")
pageHrefs = [element.div.a['href'] for element in searchBox]
return pageHrefs
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 getPage(self, url):
soup = Soup.requests(url)
if soup.find('div', class_='error'):
print("Error Page : %s" % (url))
return (0, "error", "error", 0)
articleDate = re.sub(
"\D", "",
soup.find(
'div',
class_='byline').em.next_sibling.next_sibling.get_text())[:8]
articleID = re.sub("\D", "", url)
articleTitle = soup.find("", id='article_title').get_text().strip()
# 강세, sub caption 등 중복되는 기사
etc = soup.find_all('div', class_='ab_subtitle') + soup.find_all(
'div', class_='ab_related') + soup.find_all(
'span', class_='rt') + soup.find_all('a') + soup.find_all(
'td', class_='pt_8')
photoCaption = soup.find_all(
'div', class_='html_photo_center') + soup.find_all(
'p', class_='caption')
for element in photoCaption + etc:
element.decompose()
articleTxt = soup.find(
'div', id='article_body').get_text(separator="\n").strip()
return (articleID, articleDate, articleTitle, articleTxt)
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):
count = (count-1)*10
searchUrl= "http://www.medicaltimes.com/Users4/Search/searchEach.html?nStart="+str(count)+"&KeyWord="+self.query+"&searchType=news"
soup = Soup.requests(searchUrl,parser='html.parser')
searchBox=soup.find('table', class_="news_view_contents").find_all('a', style="font-size:11pt; color:darkblue")
regex= re.compile("&nSection=(.*)")
pageHrefs=[regex.sub("",x.get('href')) for x in searchBox]
return pageHrefs
def getPageHrefs(self, count):
searchUrl = "http://search.joins.com/TotalNews?page=" + str(
count
) + "&Keyword=" + self.query + "&StartSearchDate=" + self.startDate + "&EndSearchDate=" + self.endDate + "&SortType=New&SearchCategoryType=TotalNews&PeriodType=DirectInput&ScopeType=All&ServiceCode=&MasterCode=&SourceGroupType=Joongang&ReporterCode=&ImageType=All&JplusType=All&BlogType=All&ImageSearchType=Image&MatchKeyword=" + self.query + "&IncludeKeyword=&ExcluedeKeyword="
soup = Soup.requests(searchUrl)
searchBox = soup.find('ul', class_="list_default").find_all('li')
pageHrefs = [x.find('a')['href'] for x in searchBox]
return pageHrefs
def getPageCount(self):
searchUrl = "http://www.nursenews.co.kr/main/search.asp?SearchStr=" + self.query + "&intPage=1"
soup = Soup.requests(searchUrl)
pageCount = int(
re.sub(
"\D", "",
soup.find_all("img",
align="absmiddle")[1].parent.get('href')[-3:]))
return pageCount
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.nursenews.co.kr/main/search.asp?SearchStr=" + self.query + "&intPage=" + str(
count)
soup = Soup.requests(searchUrl)
searchBox = soup.find('ul', class_='ul_board').find_all('li')
pageHrefs = [
"http://www.nursenews.co.kr/main" + x.a.get('href')[1:]
for x in searchBox
]
return pageHrefs
def getPageCount(self):
searchUrl = "http://www.medicaltimes.com/Users4/Search/searchEach.html?nStart=1&KeyWord="+self.query+"&searchType=news"
soup = Soup.requests(searchUrl,parser='html.parser')
try:
maxPageCnt=soup.find_all('tr',height='40')[0].contents[1].contents[-1].get('href')
except AttributeError:
maxPageCnt=soup.find_all('tr',height='40')[0].find_all('a')[-1].get('href')
maxPageTag = soup.find_all('img', src="http://image.medicaltimes.com/common/1_57.jpg")[0].parent
pageCount=int(re.search("nStart=[0-9]*",maxPageTag['href']).group()[7:])
return math.floor(pageCount/10)
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 getPageCount(self):
page = '1'
while 1:
searchUrl = "http://www.medipana.com/news/news_list_new.asp?Page=" + page + "&MainKind=A&NewsKind=106&vCount=20&vKind=1&sID=&sWord=" + self.query + "&sDate="
soup = Soup.requests(searchUrl, parser='html.parser')
nextButton = soup.find('img', src='../images/paging_next.gif').parent
if nextButton.name != 'a':
lastLink = soup.find_all('td', align='center')[1].find_all('a')[-1]['href']
page = re.sub("\D", "", lastLink)[:2]
break
page = re.sub("\D", "", nextButton['href'])[:2]
return int(page)
def getPage(self, url):
soup = Soup.requests(url)
photoCaption = soup.find('td', id='articleBody').find_all('table')
for element in photoCaption:
element.decompose()
articleTxt = soup.find(
'td', id='articleBody').get_text(separator="\n").strip()
articleDate = re.sub("\D", "",
soup.find('td', bgcolor="EFEFEF").get_text())[:8]
articleID = articleDate[2:] + "_" + re.sub("\D", "", url)
articleTitle = soup.find("td", class_="view_t").get_text().strip()
return (articleID, articleDate, articleTitle, articleTxt)
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 getPage(self, url):
soup = Soup.requests(url)
if soup.find('div', id='articleBody') is None:
articleTxt="사진 기사"
articleDate=re.sub("\D","", soup.select("#ND_Warp > table:nth-of-type(2)")[0].get_text())
articleTitle=soup.select("#ND_Warp > table:nth-of-type(1) > tr > td:nth-of-type(2)")[0].get_text().strip()
else:
adTags = soup.find('div', id='articleBody').find_all('table')
for element in adTags:
element.decompose()
articleTxt=soup.find('div', id='articleBody').get_text(separator="\n").strip()
articleDate=re.sub("\D","",soup.find('div',class_="info").contents[7].get_text())[:8]
articleTitle=soup.find('span',class_='headline-title').get_text().strip()
articleID=str(articleDate[2:]+re.sub("\D","",url))
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
soup = Soup.requests(url)
articleID = re.sub("\D", "", url)[2:]
articleDate = re.sub("\D", "",
soup.find('div',
class_='View_Time').get_text())[:8]
articleTitle = soup.find(
'div', class_='View_Title').strong.get_text().strip()
adTags = soup.find('div', id='CmAdContent').find_all('table')
for element in adTags:
element.decompose()
articleTxt = soup.find(
'div', id='CmAdContent').get_text(separator="\n").strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
soup = Soup.requests(url, parser='html.parser', encoding="euc-kr")
if not soup.find('body'):
print("Error url : %s"%(url))
return (0, "error", "error", 0)
articleID=re.search("ID=[0-9]*",url).group()[3:]
articleTitle=soup.find('td',class_='px21 bk fbd lh15 lt').get_text().strip()
articleDate=re.sub("\D","",soup.select("#html_head > table:nth-of-type(2) > tr:nth-of-type(2) > td:nth-of-type(1) > table > tr > td > div > table:nth-of-type(1) > tr:nth-of-type(6) > td > font")[0].get_text())[:8]
photoCaption = soup.find('td', id='NEWS_CONTENT').find_all('table')
for element in photoCaption:
element.decompose()
articleTxt=soup.find('td', id='NEWS_CONTENT').get_text(separator="\n").strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
soup = Soup.requests(url)
articleID = re.search("idx=[0-9]*", url).group()[4:]
articleDate = re.search(
"[12][0-9]{3}-[0-9]{2}-[0-9]{2}",
soup.find('div', class_='txt_1').get_text()).group() # need
articleDate = re.sub("\D", "", articleDate)
#주석 제거
for x in soup.find('div', id='neyongID').find_all('span'):
x.decompose()
articleTxt = soup.find('div',
id='neyongID').get_text(separator="\n").strip()
titleTag = soup.find('div', class_='bx_board').find('div',
class_='tit_1')
articleSubTitle = titleTag.find('div', class_='txt_s')
articleSubTitle.decompose()
articleTitle = titleTag.get_text().strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
articleID = url[37:-2]
articleDate = url[28:36] #yyyymmdd
if articleDate.isdigit() is False:
#date error
return -1
articleSoup = Soup.requests(url)
article = articleSoup.find('div', class_='article_txt')
for script in article.find_all('script'):
script.extract()
adTags = article.find_all('div', class_='article_relation') + article.find_all('span',class_='t')
photoCaption = article.find_all('div',class_='articlePhotoC') +article.find_all('div',class_='articlePhotoB') + article.find_all('div',class_='articlePhotoA')
notArticleTxt = adTags + photoCaption
for element in notArticleTxt:
element.decompose()
articleTxt = article.get_text(separator="\n").strip()
articleTitle = articleSoup.find('div', class_='article_title').find(class_='title').get_text().strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
soup = Soup.requests(url,parser='html.parser')
articleID = re.search("NewsNum=[0-9]*",url).group()[8:]
articleDate = re.sub("\D","",soup.find_all('a',class_='plan_1_1')[1].get_text())[:8]
articleTitle = soup.find('div',class_='detailL').get_text().strip()
bodyTag = soup.find('div',style="font:굴림; LINE-HEIGHT: 22px;letter-spacing:0px;text-align:justify; ")
if bodyTag.find('div') is not None:
articleTxtList = [div.get_text(separator="\n").strip() for div in bodyTag.find_all('div') ]
else:
adTags = bodyTag.find_all('table')
for element in adTags:
element.decompose()
articleTxtList = []
if len(articleTxtList) < 2:
articleTxt = bodyTag.get_text(separator="\n\n").strip()
else:
articleTxt = "\n".join(articleTxtList)
return (articleID, articleDate, articleTitle, articleTxt)
def getPage(self, url):
articleID = re.sub("\D", "", url)
soup = Soup.requests(url)
if soup.find('td', id='articleBody') is None:
#본문이 없는 기사
articleTitle = soup.find('b', class_='title').get_text()
articleTxt = "사진 기사"
articleDate = re.sub("\D", "",
soup.find('div',
class_='info').get_text())[:8]
else:
#광고 제거
adTags = soup.find('td', id='articleBody').find_all('table')
for element in adTags:
element.decompose()
articleTxt = soup.find(
'td', id='articleBody').get_text(separator="\n").strip()
articleDate = re.sub("\D", "",
soup.find('td',
class_="WrtTip").get_text())[0:8]
articleTitle = soup.find("td", id="font_title").get_text().strip()
return (articleID, articleDate, articleTitle, articleTxt)
def getPageCount(self):
searchUrl = "http://search.joins.com/TotalNews?page=1&Keyword=" + self.query + "&StartSearchDate=" + self.startDate + "&EndSearchDate=" + self.endDate + "&SortType=New&SearchCategoryType=TotalNews&PeriodType=DirectInput&ScopeType=All&ServiceCode=&MasterCode=&SourceGroupType=Joongang&ReporterCode=&ImageType=All&JplusType=All&BlogType=All&ImageSearchType=Image&MatchKeyword=" + self.query + "&IncludeKeyword=&ExcluedeKeyword="
soup = Soup.requests(searchUrl)
pageCount = soup.find('span', class_="total_number").string
return int(pageCount[2:].split(" ")[0])
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)
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 getPageHrefs(self, count):
searchUrl = "http://medifonews.com/news/search_result.html?search=" + self.query + "&search_mode=&hash=&s_title=&s_writer_name=&s_body=&s_sdate=" + self.startDate + "&s_edate=" + self.endDate + "&page=" + str(count)
soup = Soup.requests(searchUrl)
searchBox = soup.find('ul', class_='art_list_all').find_all('a')
pageHrefs = ["http://medifonews.com/news/" + x.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 getPageCount(self):
searchUrl="http://news.donga.com/search?p=1&query="+self.query+"&check_news=1&more=1&sorting=1&search_date=1&v1="+self.startDate+"&v2="+self.endDate+"&range=1"
soup = Soup.requests(searchUrl)
return math.floor(int(re.sub('\D',"", soup.find('div',class_="searchCont").h2.span.text ))//15)
def getPageCount(self):
searchUrl = "http://medifonews.com/news/search_result.html?search=" + self.query + "&search_mode=&hash=&s_title=&s_writer_name=&s_body=&s_sdate=" + self.startDate + "&s_edate=" + self.endDate + "&page=1"
soup = Soup.requests(searchUrl)
maxPageCnt = int(soup.find('i',class_='t02').get_text())
return math.floor(maxPageCnt / 20)
