def mention_to_entity(mention):
"""输入名称->实体
:param mention: 输入名称
:return: 根据名称获取歧义关系
"""
url = f'https://api.ownthink.com/kg/ambiguous?mention={mention}' # 知识图谱API，歧义关系
return get(url).text
def entity_to_knowledge(entity):
""" 实体->知识
:param entity: 实体名
:return: 根据实体获取实体知识
"""
url = f'https://api.ownthink.com/kg/knowledge?entity={entity}' # 知识图谱API，实体知识
return get(url).text
def entity_attribute_value(entity, attribute):
"""实体&属性->属性值
:param entity: 实体名
:param attribute: 属性名
:return: 根据实体、属性获取属性值
"""
url = f'https://api.ownthink.com/kg/eav?entity={entity}&attribute={attribute}' # 知识图谱API，属性值
return get(url).text
def _get_start_end():
"""获取开始期号和结束期号"""
url = 'https://datachart.500.com/ssq/history/history.shtml'
data = get(url)
response = data.content.decode('gbk')
search = re.search('<input id="end" name="end" value="(.+?)" size="10" />', response)
start, end = search.start() + 34, search.end() - 14
return 3001, response[start:end]
def get_title(self):
"""
获得资料的标题和类型
:return:
"""
data = get(self.url).content.decode('gbk')
types = re.findall(r'\'docType\': \'\w+\'', data)[0][12:-1]
title = re.findall(r'\'title\': \'.*\'', data)[0][10:-1]
return types, title, data
def math_tex(tex, file_path=None):
"""根据Tex语言生成数学公式矢量图：关于Tex语法参考：https://blog.csdn.net/qfire/article/details/81382048
:param tex: Tex语言
:param file_path: 保存矢量图的地址，后缀名一定是: xxx.svg
:return: 默认返回SVG数据。有地址保存到地址，返回True
"""
u = quote(tex)
name = hash(tex)
s = get(f'https://math.jianshu.com/math?formula={u}')
data = s.text
if not file_path:
file_path = './' + str(name) + '.svg'
w = open(file_path, 'w')
w.write(data)
w.flush()
w.close()
return True
def _ppt(self, dirs, save_path, title):
"""下载带有ppt格式"""
content_url = "https://wenku.baidu.com/browse/getbcsurl?doc_id=" + self.id + "&pn=1&rn=99999&type=ppt"
print(content_url)
content = get(content_url).content.decode('gbk')
data = json.loads(content)
start = time.time()
for size, img in enumerate(data, 1):
print('\r[下载进度]:%s%.2f%%' % ('>' * int(
(size * 50 / len(data))), float(size / len(data) * 100)))
page, zoom = img['page'], img['zoom']
urlretrieve(zoom, filename=dirs + os.sep + str(page) + '.jpg')
image_pdf(file_dir=dirs, pdf_address=save_path + os.sep + title)
shutil.rmtree(dirs)
end = time.time()
print('\n下载成功，保存地址：', save_path + os.sep + title + '.pdf', '一共耗时：',
end - start, '秒')
print('删除临时文件夹成功！')
return True
def double_data_chart(start=None, end=None):
"""爬取双色球数据,第一列数据是信息头。
:param start:开始期号：默认是第一期时间。
:param end:结束期号：默认是现在时间。
:return:二维列表。
"""
if start is None and end is None:
return double_data_chart(*_get_start_end())
header = ['期号', '红球1', '红球2', '红球3', '红球4', '红球5', '红球6', '篮球', '奖池',
'一等奖注数', '一等奖奖金', '二等奖注数', '二等奖奖金', '总投注额', '开奖日期']
ls = [header]
url = f'https://datachart.500.com/ssq/history/newinc/history.php?start={start}&end={end}'
data = get(url)
response = data.content.decode('utf-8')
for charts in re.findall(r'<tr class="t_tr1">.+?</tr>', response):
td = re.findall('<td.*?>(.+?)</td>', charts)
td.pop(9)
m = map(lambda x: x if '-' in x else int(x.replace(',', '')), td[1:])
ls.append(list(m))
return ls
