def post(url, params, cookie=None):
"""Post网站"""
headers = headers_ua()
if cookie:
headers['cookie'] = cookie
response = requests.post(url=url, data=params, headers=headers)
return response
def get(url, cookie=None):
"""Get网站"""
headers = headers_ua()
if cookie:
headers['cookie'] = cookie
response = requests.get(url=url, headers=headers)
return response
def Load_BaiDuBaiKe(name):
"""下载百度百科里面的内容信息
:param name: 百科百科名字
:return: 百度百科的文本信息
"""
url = F'https://baike.baidu.com/item/{quote(name)}'
response = requests.get(url, headers=headers_ua())
data = response.content.decode('utf-8')
return data
def _redirect_link(self, word):
"""获得重定向的链接"""
response = requests.post(self.url,
headers=headers_ua(),
data={
'wo': word,
'directGo': 1,
'nsid': 0
})
return response.url
def _not_included_data(self, word):
"""未录取句子提取"""
data_ls = []
response = requests.post(self.url,
headers=headers_ua(),
data={
'wo': word,
'directGo': 1,
'nsid': 0
})
text = response.text
soup = self._BeautifulSoup(text, features="lxml")
ls = soup.find('div', id='content').contents
for d in ls:
if not isinstance(d, str) and ('function' not in d.text):
t = d.text.replace('\xa0', '').strip()
if '造句' in t:
t = re.sub('[(（\\[【].*[^造]*造句.*[)】\\]）]', '', t)
data_ls.append(t)
return data_ls
def _get_page_data(url):
"""获得链接中的数据"""
response = requests.get(url, headers=headers_ua())
return response.text