def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)[0].strip().split()[0]
try:
t = time.strptime(t, "%Y-%m-%d")
except:
try:
t = time.strptime(t, "%Y年%m月%d日%H%M".decode('utf8'))
except:
pass
t = TimeTransform.struct_to_string(t)
return t
def parse_publishedtime(self, element):
res = element.xpath(".//div[@class='bbs f13']/text()") # 搜索百度贴吧
if res:
res = res[0]
res = res[res.index('发帖时间'.decode('utf8')) + 5:]
else:
res = element.xpath(
".//div[@class='c-abstract']//span[@class=' newTimeFactor_before_abs m']/text()"
)
if res:
res = res[0]
else:
return None
res = res.split()[0]
res = TimeTransform.struct_to_string(TimeTransform.date_to_struct(res))
return res
def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)[0].strip()
t = time.strptime(t, "%Y-%m-%d %H:%M:%S")
t = TimeTransform.struct_to_string(t)
return t
def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)[0].strip()
t = time.strptime(t, "%Y年%m月%d日 %H:%M".decode('utf8'))
t = TimeTransform.struct_to_string(t)
return t
def extract_publishedtime(self, tree):
t = [i for i in tree.xpath(self.publishedtime_xpath) if i.strip()][-1]
t = time.strptime(t, "%Y-%m-%d")
t = TimeTransform.struct_to_string(t)
return t
def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)[0].strip()
t = t[5:]
t = TimeTransform.struct_to_string(t)
return t
def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)
t = ''.join(t).strip().split()[0]
t = time.strptime(t, "%Y-%m-%d")
t = TimeTransform.struct_to_string(t)
return t
def extract_publishedtime(self, tree):
t = tree.xpath(self.publishedtime_xpath)[0].strip().split()[0]
t = t[5:]
t = time.strptime(t, "%Y-%m-%d".decode('utf8'))
t = TimeTransform.struct_to_string(t)
return t