def trans_time(self, t):
if '日'.decode('utf8') in t:
t = t[:t.index('日'.decode('utf8')) + 1]
t = TimeTransform.date_to_struct(t)
return t
if '前'.decode('utf8') in t:
if '天'.decode('utf8') in t:
delta_d = int(t[:t.index('天'.decode('utf8'))])
t = time.gmtime(time.time() - delta_d * 24 * 60 * 60)
return t
elif '小时'.decode('utf8') in t:
delta_H = int(t[:t.index('小时'.decode('utf8'))])
t = time.gmtime(time.time() - delta_H * 60 * 60)
return t
elif '分钟'.decode('utf8') in t:
delta_M = int(t[:t.index('分钟'.decode('utf8'))])
t = time.gmtime(time.time() - delta_M * 60)
return t
elif '秒'.decode('utf8') in t:
delta_S = int(t[:t.index('秒'.decode('utf8'))])
t = time.gmtime(time.time() - delta_S)
return t
return time.localtime()
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 read_keywords(self): # 读取检索的关键词及时间范围
allwords = []
for n, i in enumerate(self.text):
if i.strip():
text = i.strip()
try:
text = text.decode('utf8')
except:
try:
text = text.decode('utf8')
except:
pass
else:
continue
text = text.split(';')
times = text[0]
starttime, endtime = times.split(' ')
self.starttime = TimeTransform.date_to_struct(
Utils.transform_coding(starttime))
self.endtime = TimeTransform.date_to_struct(
Utils.transform_coding(endtime))
# self.endtime = TimeTransform.datetime_to_struct((TimeTransform.date_to_datetime(Utils.transform_coding(endtime)) + datetime.timedelta(days=1)))
if len(text) > 1:
words = list(set(text[1].split()))
if ' ' in words:
words.remove(' ')
if '' in words:
words.remove('')
allwords.extend(words)
break
else:
allwords = ['地震'.decode('utf8')]
break
self.allwords = allwords
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 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