def main():
link = ""
title = ""
state = 0
resultList = []
urlPrefix = "http://m.tstore.co.kr/mobilepoc"
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'''
<a
[^>]*
goInnerUrlDetail\(
\\
'
(?P<url>/webtoon/webtoonList[^']+)
\\
''', line, re.VERBOSE)
if m:
link = urlPrefix + m.group("url")
link = re.sub(r'&', '&', link)
state = 1
elif state == 1:
m = re.search(r'''
<dt>
(?P<title>.+)
</dt>
''', line, re.VERBOSE)
if m:
title = m.group("title")
resultList.append((link, title))
state = 0
for link, title in resultList[:5]:
print("%s\t%s" % (link, title))
def main():
clipNoList = []
volumeNo = None
memberNo = None
m = re.search(r'volumeNo=(?P<volumeNo>\d+)&memberNo=(?P<memberNo>\d+)', sys.argv[1])
if m:
volumeNo = int(m.group("volumeNo"))
memberNo = int(m.group("memberNo"))
lineList = feedmakerutil.readStdinAsLineList()
for line in lineList:
line = line.rstrip()
print(line)
failureCount = 0
link_prefix = "http://m.post.naver.com/viewer/clipContentJson.nhn?volumeNo=%d&memberNo=%d&clipNo=" % (volumeNo, memberNo)
for clipNo in range(30):
link = link_prefix + str(clipNo)
cmd = 'wget.sh "%s" utf8' % (link)
#print(cmd)
result = feedmakerutil.execCmd(cmd)
if result == False or re.search(r'"notExistClip"', result):
failureCount = failureCount + 1
if failureCount > 2:
break
else:
clipContent = json.loads(result)["clipContent"]
clipContent = re.sub(r'src="{{{[^\|]*\|/([^\|]+)\|\d+|\d+}}}"', 'src="http://post.phinf.naver.net/\1"', clipContent)
clipContent = re.sub(r'<img src=\'http://static.post.naver.net/image/im/end/toast_flick.png\'/>', '', clipContent)
print(clipContent)
def main():
link = ""
title = ""
urlPrefix = ""
state = 0
resultList = []
urlPrefix = ""
numOfRecentFeeds = 1000
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'window\.location\.href\s*=\s*"(?P<url>[^"]+)"', line)
if m:
urlPrefix = + m.group("url")
state = 1
elif state == 1:
matches = m.findall(r'<option (?:selected="" )?value="(?P<url>\d+)">(?P<title>[^<]+)</option>', line)
for match in matches:
link = urlPrefix + match[1]
title = match[0]
resultList.append((link, title))
for (link, title) in resultList[-numOfRecentFeeds:]:
print("%s\t%s" % (link, title))
def main():
state = 0
numOfRecentFeeds = 10
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
lineList = feedmakerutil.readStdinAsLineList()
resultList = []
for line in lineList:
if state == 0:
m1 = re.search(r'"path"\s*:\s*"(?P<prefix>[^"]+)"', line)
if m1:
prefix = m1.group("prefix")
state = 1
elif state == 1:
m2 = re.search(r'{"name"\s*:\s*"(?P<link>\d[^"]+.md)"}', line)
if m2:
link = "http://teamsego.github.io/github-trend-kr/" + prefix + "/" + m2.group("link")
title = m2.group("link")
resultList.append((link, title))
m3 = re.search(r'{"volume":', line)
if m3:
lineList.insert(0, line)
state = 0
#print(state, end=' ')
for (link, title) in resultList[-numOfRecentFeeds:]:
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
state = 0
numOfRecentFeeds = 10
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
lineList = feedmakerutil.readStdinAsLineList()
resultList = []
for line in lineList:
if state == 0:
m = re.search(r'<li class="list viewerLinkBtn (?:pointer )?list_[HV][^>]*data-productid="(?P<id>\d+)', line)
if m:
productid = m.group("id")
link = "http://page.kakao.com/viewer?productId=" + productid
state = 1
elif state == 1:
m = re.search(r'<span class="Lfloat (?:listTitle )?ellipsis">', line)
if m:
state = 2
elif state == 2:
m = re.search(r'^\s*(?P<title>\S+.*\S+)\s*$', line)
if m:
title = m.group("title")
title = re.sub(r'&(lt|gt);', '', title)
resultList.append((link, title))
state = 0
for (link, title) in resultList[:numOfRecentFeeds]:
print("%s\t%s" % (link, title))
def main():
encoding = "utf-8"
isEnd = False
numOfRecentFeeds = 30
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
# get a url of first list page
pageContentLineList = feedmakerutil.readStdinAsLineList()
resultList = printArticleUrlList(pageContentLineList)
nextPageUrl, isEnd = getNextPageUrl(pageContentLineList, "articleTypeList")
# get url list from first list page (iterative)
while len(resultList) < numOfRecentFeeds:
pageContent = getPageContent(nextPageUrl, encoding)
pageContentLineList = re.split(r'\n', pageContent)
resultList.extend(printArticleUrlList(pageContentLineList))
nextPageUrl, isEnd = getNextPageUrl(pageContentLineList, "cateList")
if isEnd:
break
for (link, title) in resultList[:numOfRecentFeeds]:
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
state = 0
resultList = []
urlPrefix = "http://music.naver.com"
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'<a\s+class="[^"]+"\s+href=\"(?P<url>/todayMusic/index\.nhn[^\"]+)\"[^>]*>', line)
if m:
link = urlPrefix + m.group("url")
link = re.sub(r'&', '&', link)
state = 1
elif state == 1:
m = re.search(r'<span\s+class="[^"]+"\s+title=\"[^\"]+\"[^>]*>(?P<title>[^<]+)</span>', line)
if m:
title = m.group("title")
resultList.append((link, title))
state = 0
count = 0
for link, title in resultList:
print("%s\t%s" % (link, title))
count += 1
if count >= 7:
break
def main():
secondPageUrl = ""
for line in feedmakerutil.readStdinAsLineList():
line = line.rstrip()
m = re.search(
r"<a href='(?P<secondPageUrl>http://[^']+)'[^>]*><img src='http://cwstatic\.asiae\.co\.kr/images/cartoon/btn_s\.gif'/>",
line,
)
if m:
secondPageUrl = m.group("secondPageUrl")
else:
m = re.search(r"<a href='(?P<secondPageUrl>http://stoo.asiae.co.kr/cartoon/view.htm[^']*)'>2페이지</a>", line)
if m:
secondPageUrl = m.group("secondPageUrl")
else:
m = re.search(r"<img src='(?P<imgUrl>http://cwcontent[^']+)'.*/>", line)
if m:
imgUrl = m.group("imgUrl")
print("<img src='%s' width='100%%'/>" % (imgUrl))
if secondPageUrl != "":
cmd = "wget.sh '%s' | extract_element.py extraction" % (secondPageUrl)
# print(cmd)
result = feedmakerutil.execCmd(cmd)
if result:
for line in result.split("\n"):
m = re.search(r"<img\s*[^>]*src=(?:\'|\")(?P<imgUrl>http://cwcontent[^\'\"]+)(?:\'|\").*/>", line)
if m:
imgUrl = m.group("imgUrl")
print("<img src='%s' width='100%%'/>" % (imgUrl))
def main():
link = ""
title = ""
icon = ""
state = 0
lineList = feedmakerutil.readStdinAsLineList()
for line in lineList:
if state == 0:
m1 = re.search(r'<a href="(?P<link>[^"]+mag_id=\d+)">', line)
if m1:
link = m1.group("link")
link = re.sub(r'&', '&', link)
link = "http://www.cine21.com" + link
state = 1
elif state == 1:
m2 = re.search(r'<span class="tit">(?P<title>[^<]+)</span>', line)
if m2:
title = m2.group("title")
if re.search(r'(대학교|영화학|모집)', title):
continue
title = re.sub(r'<', '"', title)
title = re.sub(r'>', '"', title)
print("%s\t%s" % (link, title))
state = 0
def main():
link_prefix = "http://cartoon.media.daum.net/m/webtoon/viewer/"
link = ""
title = ""
nickname = ""
numOfRecentFeeds = 30
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == "-n":
numOfRecentFeeds = int(a)
lineList = feedmakerutil.readStdinAsLineList()
resultList = []
for line in lineList:
p = re.compile(r'"id":(?P<id>\d+),"episode":(?P<episode>\d+),"title":"(?P<title>[^"]+)",')
for m in p.finditer(line):
md = m.groupdict()
id = md["id"]
episode = int(md["episode"])
title = md["title"]
link = link_prefix + id
title = "%04d. %s" % (episode, title)
resultList.append((link, title))
for (link, title) in resultList[:numOfRecentFeeds]:
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
urlPrefix = "http://m.tstore.co.kr/mobilepoc/webtoon/webtoonDetail.omp?prodId="
resultList = []
numOfRecentFeeds = 1000
count = 0
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
for line in feedmakerutil.readStdinAsLineList():
matches = re.findall(r'''
[^}]*,
"prodId"\s*:\s*"\s*([^"]+)\s*",
[^}]*,
"prodNm"\s*:\s*"\s*([^"]+)\s*",
''', line, re.VERBOSE)
for match in matches:
link = urlPrefix + match[0]
title = match[1]
if link and title:
resultList.append((link, title))
for (link, title) in resultList[-numOfRecentFeeds:]:
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
episodeNum = ""
state = 0
urlPrefix = "http://sports.chosun.com/cartoon"
resultList = []
numOfRecentFeeds = 1000
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'<li class="section1">(?P<episodeNum>[^<]+)</li>', line)
if m:
episodeNum = m.group("episodeNum")
state = 1
elif state == 1:
m = re.search(r'<li class="section2"><a href="(?P<url>[^"]+)">\[[^\]]+\] (?P<title>[^<]+)</a></li>', line)
if m:
url = m.group("url")
title = m.group("title")
link = re.sub(r'&', '&', link)
link = urlPrefix + url
title = episodeNum + " " + title
resultList.append((link, title))
for link, title in resultList[-numOfRecentFeeds:]:
print("%s\t%s" % (link, title))
def main():
link = ""
episodeNum = ""
title = ""
state = 0
urlPrefix = "http://comics.nate.com"
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'<a href="(?P<url>/webtoon/detail\.php\?[^"]+)&category=\d+">', line)
if m:
url = urlPrefix + m.group("url")
link = re.sub(r"&", "&", url)
state = 1
elif state == 1:
m = re.search(r'<span class="tel_episode">(?P<episodeNum>.+)</span>', line)
if m:
episodeNum = m.group("episodeNum")
state = 2
elif state == 2:
m = re.search(r'<span class="tel_title">(?P<title>.+)</span>', line)
if m:
title = episodeNum + " " + m.group("title")
print("%s\t%s" % (link, title))
state = 0
def main():
imgHost = ""
imgPath = ""
imgIndex = -1
imgExt = "jpg"
pageUrl = sys.argv[1]
for line in feedmakerutil.readStdinAsLineList():
line = line.rstrip()
if re.search(r"<(meta|style)", line):
print(line)
else:
m = re.search(r"<img src='http://(?P<imgHost>imgcomic.naver.(?:com|net))/(?P<imgPath>[^']+_)(?P<imgIndex>\d+)\.(?P<imgExt>jpg|gif)", line, re.IGNORECASE)
if m:
imgHost = m.group("imgHost")
imgPath = m.group("imgPath")
imgIndex = int(m.group("imgIndex"))
imgExt = m.group("imgExt")
print("<img src='http://%s/%s%d.%s' width='100%%'/>" % (imgHost, imgPath, imgIndex, imgExt))
else:
m = re.search(r"<img src='http://(?P<imgHost>imgcomic.naver.(?:com|net))/(?P<imgPath>[^']+)\.(?P<imgExt>jpg|gif)", line, re.IGNORECASE)
if m:
imgHost = m.group("imgHost")
imgPath = m.group("imgPath")
imgExt = m.group("imgExt")
print("<img src='http://%s/%s.%s' width='100%%'/>" % (imgHost, imgPath, imgExt))
if imgPath != "" and imgIndex >= 0:
# add some additional images loaded dynamically
for i in range(60):
imgUrl = "http://%s/%s%d.%s" % (imgHost, imgPath, i, imgExt)
cmd = 'wget.sh --spider --referer "%s" "%s"' % (pageUrl, imgUrl)
result = feedmakerutil.execCmd(cmd)
if result:
print("<img src='http://%s/%s%d.%s' width='100%%'/>" % (imgHost, imgPath, i, imgExt))
def main():
link = ""
title = ""
linkPrefix = "http://comic.mt.co.kr/"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'''
<li>
<a\s+href="\./(?P<link>comicView\.htm[^"]+)">
<img\s+height="\d+"\s+src="[^"]+"\s+width="\d+"\s*/>
</a>
<p\ class="[^"]+">
(?P<title1>[^<]+)
<br/?>
<b>
(?P<title2>[^<]*)
</b>
(?:</br>)?
</p>
</li>
''', line, re.VERBOSE)
if m:
link = linkPrefix + m.group("link")
title = m.group("title1") + " " + m.group("title2")
link = re.sub(r"&", "&", link)
link = re.sub(r"&nPage=[^&]*", "", link)
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
url = ""
cartoonId = 0
episodeId = 0
episodeNum = 0
state = 0
urlPrefix = "http://sports.khan.co.kr"
resultList = []
numOfRecentFeeds = 1000
optlist, args = getopt.getopt(sys.argv[1:], "n:")
for o, a in optlist:
if o == '-n':
numOfRecentFeeds = int(a)
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'document\.location\.href\s*=\s*"(?P<url>[^"]+)"', line)
if m:
url = m.group("url")
state = 1
elif state == 1:
matches = re.findall(r"<option value='(?P<cartoonId>\d+)\|(?P<episodeId>\d+)(?:\|\d+)?'(?: selected)?>(?P<title>[^<]+)</option>", line)
for match in matches:
cartoonId = match[0]
episodeId = match[1]
title = match[2]
link = urlPrefix + url + cartoonId + "&page=" + episodeId
link = re.sub(r'&', '&', link)
resultList.append((link, title))
for (link, title) in resultList[-numOfRecentFeeds:]:
print("%s\t%s" % (link, title))
def main():
link = ""
urlPrefix = "http://navercast.naver.com/"
title = ""
state = 0
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'<a class="card" href="/?(?P<url>contents\.nhn\?contents_id=\d+[^"]*)"[^>]*>', line)
if m:
url = m.group("url")
url = re.sub(r"&", "&", url)
link = urlPrefix + url
state = 1
elif state == 1:
m = re.search(r'<strong>(?P<mainTitle>[^<]+)</strong><span(?: alt="[^"]+" title="(?P<subTitle1>[^"]+)")?>(?P<subTitle2>.*)</span>', line)
if m:
if m.group("subTitle1"):
title = m.group("mainTitle") + " - " + m.group("subTitle1")
else:
title = m.group("mainTitle") + " - " + m.group("subTitle2")
print("%s\t%s" % (link, title))
state = 0
link = ""
title = ""
def main():
pageUrl = sys.argv[1]
urlPrefix = ""
dataUrl = ""
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r"jpg: '(?P<urlPrefix>[^']+\/){=filename}\?type=[^']+'", line)
if m:
urlPrefix = m.group("urlPrefix")
else:
m = re.search(r"documentURL:\s*'(?P<dataUrl>[^']+)'", line)
if m:
dataUrl = m.group("dataUrl")
break
if not dataUrl or urlPrefix:
die("can't get a data url from input")
cmd = "wget.sh '%s' utf8 | gunzip 2> /dev/null || wget.sh '%s' utf8" % (dataUrl, dataUrl)
#print(cmd);
with subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE) as p:
for line in p.stdout:
line = line.rstrip()
matches = re.findall(r"[^\"]+\"\s*:\s*\"(assets/still/[^\"]+\.(?:png|jpg))\"", line)
for match in matches:
imgUrl = urlPrefix + match[0]
print("<img src='%s' width='100%'/>" % (imgUrl))
def main():
lineList = feedmakerutil.readStdinAsLineList()
for line in lineList:
matches = re.findall(r'nickname":"([^"]+)"[^"]*"title":"([^"]+)', line)
for match in matches:
link = "http://cartoon.media.daum.net/webtoon/view/" + match[0]
title = match[1]
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
urlPrefix = "http://sports.news.naver.com"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<a href="(?P<url>/magazineS/index\.nhn\?id=\d+)">(?P<title>[^<]+)</a>', line)
if m:
link = urlPrefix + m.group("url")
title = m.group("title")
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
urlPrefix = "http://sports.donga.com/cartoon"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<li(?: class="first")?><a href="(?P<url>\?cid=[^"]+)"><img alt="(?P<title>[^"]+)"', line)
if m:
link = urlPrefix + m.group("url")
title = m.group("title")
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<strong><a href="(?P<url>http://sports.khan.co.kr/comics/cartoon_view.html\?comics=b2c&sec_id=\d+)">(?P<title>[^<]+)</a></strong>', line)
if m:
link = m.group("url")
title = m.group("title")
link = re.sub(r'&', '&', link)
print("%s\t%s" % (link, title))
def main():
urlDomain = getUrlDomainFromConfig();
lineList = feedmakerutil.readStdinAsLineList()
for line in lineList:
matches = re.findall(r'<a href="/(\d+)"[^>]*>([^<]*)</a>', line)
for match in matches:
link = urlDomain + match[0]
title = match[1]
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
linkPrefix = "http://movie.daum.net/movieinfo/news/"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r"<h5><a\s+class=\"[^\"]+\"\s+href=\"(?P<link>movieInfoArticleRead\.do[^\"]+)\"[^>]*>(?P<title>.+)</a></h5>", line)
if m:
link = linkPrefix + m.group("link")
link = re.sub(r"&", "&", link)
title = m.group("title")
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
state = 0
urlPrefix = "http://comic.naver.com"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<a href="(?P<url>/webtoon/list.nhn\?titleId=\d+)[^"]*"[^>]*><img[^>]*title="(?P<title>[^"]+)"[^>]*/?>', line)
if m:
url = m.group("url")
title = m.group("title")
link = urlPrefix + url
print("%s\t%s" % (link, title))
def main():
state = 0
for line in feedmakerutil.readStdinAsLineList():
line = line.rstrip()
if state == 0:
pat = r"<img src=\"http://imgnews.naver.(com|net)/image/sports/\d+/magazineS/magazine_content/magazineS_\d+/\d+_file_image_0.jpg\" width=\"67\" height=\"9\" alt=\"[^\"]+\" />"
m = re.search(pat, line)
if m:
line = re.sub(pat, "PEOPLE", line)
state = 1
elif state == 1:
pat = r"<img src=\"http://imgnews.naver.(com|net)/image/sports/\d+/magazineS/magazine_content/magazineS_\d+/\d+_file_image_0.jpg\" width=\"102\" height=\"10\" alt=\"[^\"]+\" />"
m = re.search(pat, line)
if m:
line = re.sub(pat, "SPECIAL REPORT", line)
state = 2
elif state == 2:
pat = r"<img src=\"http://imgnews.naver.(com|net)/image/sports/\d+/magazineS/magazine_content/magazineS_\d+/\d+_file_image_0.jpg\" width=\"57\" height=\"10\" alt=\"[^\"]+\" />"
m = re.search(pat, line)
if m:
line = re.sub(pat, "COLUMN", line)
state = 3
elif state == 3:
pat = r"<h2><img src=\"http://imgnews.naver.(com|net)/image/sports/\d+/magazineS/magazine_content/magazineS_\d+/\d+_file_image_0.jpg\" width=\"58\" height=\"10\" alt=\"[^\"]+\" /></h2>.*"
m = re.search(pat, line)
if m:
line = re.sub(pat, "", line)
state = 4
elif state == 4:
pat = r"<img src=\"http://imgnews.naver.(com|net)/image/sports/\d+/magazineS/magazine_content/magazineS_\d+/\d+_file_image_0.jpg\" width=\"29\" height=\"10\" alt=\"[^\"]+\" />"
m = re.search(pat, line)
if m:
line = re.sub(pat, "POLL", line)
state = 5
else:
continue
elif state == 5:
pat = r"^<div><ul>"
m = re.search(pat, line)
if m:
line = re.sub(pat, "<h2>ZOOM IN</h2><ul>", line)
state = 6
elif state == 6:
pat = r"^</li></ul></div>"
m = re.search(pat, line)
if m:
line = re.sub(pat, "</li></ul>", line)
break
print(line)
def main():
link = ""
title = ""
urlPrefix = "http://sports.chosun.com/cartoon/sub_list.htm?title="
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<li><a href="[^"]*title=(?P<url>[^"&]+)[^"]*"><img alt="(?P<title>[^"]+)"', line)
if m:
if m.group("title") == "coin":
# 오늘의운세는 skip
continue
link = urlPrefix + m.group("url")
title = m.group("title")
link = re.sub(r'&', '&', link)
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
urlPrefix = "http://stoo.asiae.co.kr"
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'<a href="(?P<url>/cartoon/list.htm\?sec=\d+)"', line)
if m:
url = m.group("url")
link = re.sub(r'&', '&', link)
link = urlPrefix + url
else:
m = re.search(r'<dt class="desc">(?P<title>[^<]+)</dt>', line)
if m:
title = m.group("title")
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
urlPrefix = "http://blog.naver.com/PostView.nhn?blogId="
for line in feedmakerutil.readStdinAsLineList():
m = re.search(r'"blogId"\s*:\s*"(?P<blogId>[^"]+)"', line)
if m:
urlPrefix = urlPrefix + m.group("blogId") + "&logNo="
matches = re.findall(r'"logNo":"(\d+)","title":"([^"]+)",', line)
for match in matches:
logNo = match[0]
title = urllib.parse.unquote(match[1])
title = re.sub(r"\+", " ", title)
title = re.sub(r""", "'", title)
title = re.sub(r"&(lt|gt);", "", title)
link = urlPrefix + logNo
print("%s\t%s" % (link, title))
def main():
link = ""
title = ""
state = 0
urlPrefix = "http://comics.nate.com"
for line in feedmakerutil.readStdinAsLineList():
if state == 0:
m = re.search(r'<a class="wtl_toon" href="(?P<url>/webtoon/list.php\?btno=\d+)[^"]*">', line)
if m:
link = 1
link = urlPrefix + m.group("url")
state = 1
elif state == 1:
m = re.search(r'<span class="wtl_img"><i></i><img alt="(?P<title>[^"]+)"', line)
if m:
title = m.group("title")
print("%s\t%s" % (link, title))
state = 0