def parse(self):
data = mylib.myurl(self.url)
data[0] = data[0].split("=")[1].strip()
data[-1] = data[-1].strip(";")
data_str = "".join(data)
data_image = data[1].split(":")[0].strip("\"")
ret = urlparse.urljoin(self.url, data_image)
self.write(ret)
def parse(self):
data = mylib.myurl(self.url)
ret = ""
flag = False
for line in data:
if "divList" in line:
ret = line
break
self.write(ret)
def parse(self, write=True):
cxt = Context(self.url)
data = mylib.myurl(self.url)
for line in data:
cxt.do(line)
if write:
self.write(cxt.result())
else:
return cxt.result()
def parse(self):
data = mylib.myurl(self.url)
image_line = ""
for line in data:
if "USEMAP" in line:
image_line = line
break
image_str = image_line.split()[1].split("=")[1].strip("\"")
ret = urlparse.urljoin(self.url, image_str)
self.write(ret)
def parse(self):
data = mylib.myurl(self.url)
ret = ""
for line in data:
m = re.search("src=.+</iframe>", line)
if m != None:
url = m.group(0).split("?")[0].strip("src=")
ret = urlparse.urljoin(self.url, url)
break
self.write(ret)
def retryUrl(url):
cnt = 0
while cnt < 3:
try:
data = mylib.myurl(url)
return data
except:
print "retry:", cnt
pass
cnt += 1
return []
def parse(self):
data = mylib.myurl(self.url)
data_ret = ""
contents = []
for line in data:
if "galleries-slide-sub-title1" in line:
concert = {}
concert["url_content"] = self.extractURL(line)
self._parse_content(concert["url_content"], concert)
contents.append(copy.deepcopy(concert))
self.write(contents)
def parse(self):
data = mylib.myurl(self.url)
data_ret = ""
contents = []
for line in data:
if "galleries-slide-sub-title1" in line:
concert = {}
concert['url_content'] = self.extractURL(line)
self._parse_content(concert['url_content'], concert)
contents.append(copy.deepcopy(concert))
self.write(contents)
def parse(self):
data = mylib.myurl(self.url)
ret = ""
flag = False
for line in data:
if "<center>" in line or flag == True:
ret += line
flag = True
if "</center>" in line:
ret += line
break
self.write(ret)
def parse(self):
data = mylib.myurl(self.url)
s = 0
for i in range(len(data)):
if "BoxTable" in data[i]:
s = i
break
data_clean = data[s:]
for line in data_clean:
print line
self.write(data_clean)
def parse(self):
data = mylib.myurl(self.url)
ret = ""
flag = False
for line in data:
if "<table" in line:
ret += line
flag = True
if "</table>" in line:
ret += line
break
if flag:
ret += line
print ret
self.write(ret)
def parse(self):
data = mylib.myurl(self.url)
data_ret = ""
for line in data:
if "shows_list" in line:
data_ret = line
break
contents = self.extractPoster(data_ret)
self.extractPrice(data_ret, contents)
self.extractDate(data_ret, contents)
if len(contents) > 0:
self.write(contents)
return 0
else:
return 1
def parse(self):
data = mylib.myurl(self.url)
data_ret = ""
for line in data:
if "shows_list" in line:
data_ret = line
break
contents = self.extractPoster(data_ret)
self.extractPrice(data_ret, contents)
self.extractDate(data_ret, contents)
if len(contents) > 0:
self.write(contents)
return 0
else:
return 1
def parse(self):
data = mylib.myurl(self.url)
ret = ""
flag = False
for line in data:
line = line.decode("big5")
line = line.encode("utf=8")
if "<table" in line:
ret += line
flag = True
if flag:
ret += line
if "</table>" in line:
break
self.write(ret)
def parse(self):
data = mylib.myurl(self.url)
flag = False
url_map = {}
for line in data:
if "News_NewsList" in line:
title = re.search("target=\"\">.+</a>", line)
key = title.group(0).split(">")[1].rstrip("</a>")
m = re.search("href=\".+\"", line)
if m != None:
target_url = self.host + m.group(0).split()[0].lstrip("href=\"").rstrip("\"")
url_map[key] = [target_url.replace("amp;","")]
for key in url_map.keys():
kgs = kmdn_gov_sub.Parser({"url" : url_map[key][0]})
time.sleep(random.randint(3,5))
url_map[key].append(kgs.parse(False))
self.write(url_map)
def _parse_content(self, url, content):
print url
data = mylib.myurl(url)
data_ret = ""
place = 0
price = 0
start_date = 0
start_time = 0
for line in data:
if "<title>" in line:
searchObj = re.search(r'<title>(.*?)</title>', line,
re.M | re.I | re.S)
if searchObj:
content['title'] = searchObj.group(1)
if "alignnone" in line:
searchObj = re.search(r'src="(.*?)"', line, re.M | re.I | re.S)
if searchObj:
content['url_image'] = searchObj.group(1)
content['image_id'] = searchObj.group(1).split("/")[-1]
if place == 1 and "</p>" in line:
content['place'] = line.strip().rstrip("</p>")
place = 0
if price == 1 and '</p>' in line:
content['price'] = line.strip().rstrip("</p>")
price = 0
if start_date == 1 and '</p>' in line:
content['start_date'] = line.strip().rstrip("</p>")
start_date = 0
if start_time == 1 and '</p>' in line:
content['start_time'] = line.strip().rstrip("</p>")
start_time = 0
if "演出場地" in line:
place = 1
if "演出票價" in line:
price = 1
if "演出日期" in line:
start_date = 1
if "演出開始" in line:
start_time = 1
def _parse_content(self, url, content):
print url
data = mylib.myurl(url)
data_ret = ""
place = 0
price = 0
start_date = 0
start_time = 0
for line in data:
if "<title>" in line:
searchObj = re.search(r"<title>(.*?)</title>", line, re.M | re.I | re.S)
if searchObj:
content["title"] = searchObj.group(1)
if "alignnone" in line:
searchObj = re.search(r'src="(.*?)"', line, re.M | re.I | re.S)
if searchObj:
content["url_image"] = searchObj.group(1)
content["image_id"] = searchObj.group(1).split("/")[-1]
if place == 1 and "</p>" in line:
content["place"] = line.strip().rstrip("</p>")
place = 0
if price == 1 and "</p>" in line:
content["price"] = line.strip().rstrip("</p>")
price = 0
if start_date == 1 and "</p>" in line:
content["start_date"] = line.strip().rstrip("</p>")
start_date = 0
if start_time == 1 and "</p>" in line:
content["start_time"] = line.strip().rstrip("</p>")
start_time = 0
if "演出場地" in line:
place = 1
if "演出票價" in line:
price = 1
if "演出日期" in line:
start_date = 1
if "演出開始" in line:
start_time = 1
def parse(self):
data = mylib.myurl(self.url)
ret_list = []
inflag = False
ret = ""
for line in data:
"""
if "rowspan=\"2\"" in line:
pass
#print line.split(">")[1].split("<")[0].decode("utf8")
"""
if "<tbody><tr>" in line:
inflag = True
ret += line
if "row 1 start" in line or "</table>" in line:
ret += line
ret_list.append(ret)
ret = ""
elif inflag:
ret += line
head = ret_list[0].split("<tbody>")[2]
kmdn_data = ret_list[-3].replace("../../", "http://www.cwb.gov.tw//V7/")
ret = [head, kmdn_data]
self.write(ret)
