def parse(self, task, input_file):
"""parse city xml file
Args:
task: HttpTask or FileTask,
input_file: file, response body or file
Yields:
item: Item, result of parse
task: Task, new task
"""
self.logger.info("city parser begin to parse")
try:
tree = etree.parse(input_file)
elems = tree.xpath("//CityDetail")
for elem in elems:
chinese_name = remove_white(elem.findtext("CityName", ""))
city_code = get_city_code(
remove_white(elem.findtext("CityName", "")))
ctrip_code = remove_white(elem.findtext("City", ""))
if len(chinese_name) <= 0 or not city_code or \
len(city_code) <= 0 or len(ctrip_code) <= 0:
self.logger.info("invaliade city chinese_name:%s "
"citycode:%s ctrip_code:%s" %
(chinese_name, city_code, ctrip_code))
continue
yield build_hotels_task_for_city(ctrip_code, city_code,
chinese_name)
yield CityItem(chinese_name, ctrip_code, city_code)
except Exception, e:
self.logger.error("city parser extract error:%s" % e)
def parse(self, task, input_file):
"""parse city xml file
Args:
task: HttpTask or FileTask,
input_file: file, response body or file
Yields:
item: Item, result of parse
task: Task, new task
"""
self.logger.info("city parser begin to parse")
try:
tree = etree.parse(input_file)
elems = tree.xpath("//CityDetail")
for elem in elems:
chinese_name = remove_white(elem.findtext("CityName", ""))
city_code = get_city_code(remove_white(
elem.findtext("CityName", "")))
ctrip_code = remove_white(elem.findtext("City", ""))
if len(chinese_name) <= 0 or not city_code or \
len(city_code) <= 0 or len(ctrip_code) <= 0:
self.logger.info("invaliade city chinese_name:%s "
"citycode:%s ctrip_code:%s"
% (chinese_name, city_code, ctrip_code))
continue
yield build_hotels_task_for_city(ctrip_code, city_code,
chinese_name)
yield CityItem(chinese_name, ctrip_code, city_code)
except Exception, e:
self.logger.error("city parser extract error:%s" % e)
def parse(self, task, input_file):
"""解析函数
Args:
task:Task, 任务描述
input_file:File, 文件对象
Yields:
Item
Task
"""
tree = html.parse(input_file)
citys = tree.xpath("//p[@id='citypid']/text()")
citys = citys[0] if citys is not None and len(citys) > 0 else ""
for city in citys.split(u","):
city_english_name = remove_white(city)
if len(city_english_name) > 0:
city_item = CityItem("", city_english_name,
get_city_code(city_english_name))
if city_item.english_name and city_item.city_code:
yield city_item
http_request = HTTPRequest(url=build_url_by_city_name(
city_item.english_name),
connect_timeout=20,
request_timeout=240)
new_task = HttpTask(
http_request,
callback='DealParser',
max_fail_count=5,
kwargs={'citycode': city_item.city_code})
yield new_task
def parse(self, task, input_file):
"""解析函数
Args:
task:Task, 任务描述
input_file:File, 文件对象
Yields:
Item
Task
"""
tree = html.parse(input_file)
citys = tree.xpath("//p[@id='citypid']/text()")
citys = citys[0] if citys is not None and len(citys) > 0 else ""
for city in citys.split(u","):
city_english_name = remove_white(city)
if len(city_english_name) > 0:
city_item = CityItem("", city_english_name,
get_city_code(city_english_name))
if city_item.english_name and city_item.city_code:
yield city_item
http_request = HTTPRequest(
url=build_url_by_city_name(city_item.english_name),
connect_timeout=20, request_timeout=240)
new_task = HttpTask(http_request, callback='DealParser',
max_fail_count=5,
kwargs={'citycode': city_item.city_code})
yield new_task
def _extract_content_text(data_element):
"""用于解析出content_text值
Args:
data_element: Element, 节点
Returns:
content_text: str, 已处理的str
"""
content_text = data_element.findtext("content_text", "")
content_text = content_text.replace("-", "")\
.replace(" ", " ")\
.replace("<br />", "N_Line")\
.replace("<br/>", "N_Line")
tree = etree.HTML(content_text)
temp_texts = []
for text in tree.itertext():
stripped_text = remove_white(text)
if len(stripped_text) > 0:
temp_texts.append(stripped_text)
if len(temp_texts) > 0:
last_text = temp_texts.pop().strip()
if last_text.endswith("N_Line") and len(last_text) > 6:
temp_texts.append(last_text[:-6])
else:
temp_texts.append(last_text)
if len(temp_texts) > 0:
texts = [u"-"]
texts.extend(temp_texts)
complete_texts = "".join(texts)
else:
complete_texts = ""
new_text = re.sub("\s*N_Line\s*", "N_Line-", complete_texts)
return new_text
def _extract_content_text(data_element):
"""用于解析出content_text值
Args:
data_element: Element, 节点
Returns:
content_text: str, 已处理的str
"""
content_text = data_element.findtext("content_text", "")
content_text = content_text.replace("-", "")\
.replace(" ", " ")\
.replace("<br />", "N_Line")\
.replace("<br/>", "N_Line")
tree = etree.HTML(content_text)
temp_texts = []
for text in tree.itertext():
stripped_text = remove_white(text)
if len(stripped_text) > 0:
temp_texts.append(stripped_text)
if len(temp_texts) > 0:
last_text = temp_texts.pop().strip()
if last_text.endswith("N_Line") and len(last_text) > 6:
temp_texts.append(last_text[:-6])
else:
temp_texts.append(last_text)
if len(temp_texts) > 0:
texts = [u"-"]
texts.extend(temp_texts)
complete_texts = "".join(texts)
else:
complete_texts = ""
new_text = re.sub("\s*N_Line\s*", "N_Line-", complete_texts)
return new_text
def _extract_place(data_element):
"""从api中解析出地址信息列表
Args:
tree:Etree, 树节点
Returns:
places:List, 地址列表
"""
places = data_element.xpath("places//place")
item_places = []
for place in places:
place_info = {
'place_name': remove_white(place.findtext("place_name", "")),
'address': remove_white(place.findtext("address", "")),
'place_phone': remove_white(place.findtext("place_phone", "")),
'longitude': remove_white(place.findtext("longitude", "")),
'latitude': remove_white(place.findtext("latitude", "")),
'open_time': remove_white(place.findtext("open_time", "")),
}
item_places.append(place_info)
return item_places
def _extract_place(data_element):
"""从api中解析出地址信息列表
Args:
tree:Etree, 树节点
Returns:
places:List, 地址列表
"""
places = data_element.xpath("places//place")
item_places = []
for place in places:
place_info = {
'place_name': remove_white(place.findtext("place_name", "")),
'address': remove_white(place.findtext("address", "")),
'place_phone': remove_white(place.findtext("place_phone", "")),
'longitude': remove_white(place.findtext("longitude", "")),
'latitude': remove_white(place.findtext("latitude", "")),
'open_time': remove_white(place.findtext("open_time", "")),
}
item_places.append(place_info)
return item_places
