def __get_second_data(self, url):
res = requests.get(url)
if 304 >= res.status_code >= 200:
try:
soup = BeautifulSoup(res.text, 'lxml')
except IndexError and KeyError:
return BaseHandler().write_error()
return BaseHandler().write_error()
def get_data(self):
res = requests.get(url=self.url)
if 304 >= res.status_code >= 200:
data = json.loads(res.text)['result']
count = len(data)
return BaseHandler().write_list(code=const.SUCCESS_CODE,
message=const.SUCCESS_MESSAGE,
count=count,
data=data)
return BaseHandler().write_error()
def search():
word = request.args.get('word')
if not word:
return BaseHandler().write_error(const.FAIL_CODE,
const.KEYWORD_NONE_MESSAGE)
try:
page = request.args.get('page')
return Search(word=word, page=page).search()
except Exception:
return BaseHandler().write_error(const.FAIL_CODE, const.FAIL_CODE)
def __filter_normal_video(self, data):
result = {}
soup = BeautifulSoup(data, 'lxml')
try:
mid = soup.select('.u-face > a')[0][
'mid'] # mid可以根据http://space.bilibili.com/<mid>进入作者空间
author_info = self.__get_author_info(mid)
play_info = self.__get_play_info()
title = soup.select('.info > .v-title')[0].get_text()
tag_list = []
for tag in soup.select('.tag-list > li'):
tag_list.append(tag.select('a')[0].get_text())
desc = soup.select('#v_desc')[0].get_text()
cid = 0
re_findall = re.findall(
r'cid=(\d+)',
soup.select('.scontent > script')[0].string)
if re_findall:
cid = re_findall[0] # 获取视频真正链接 - 弹幕 的重要参数
video_url_info = self.__get_video_url(cid)
create_time = str(soup.select('time')[0]['datetime']).replace(
'T', ' ')
category = None
category_url = None
for item in soup.select('.tminfo > span'):
category = item.select('a')[0].string
category_url = 'http://www.bilibili.com%s' % item.select(
'a')[0]['href']
# 相关视频
relative_list = self.__get_relative_video()
result['author_info'] = author_info
result['play_info'] = play_info
result['title'] = title
result['tag_list'] = tag_list
result['desc'] = desc
result['cid'] = int(cid)
result['create_time'] = create_time
result['video_info'] = video_url_info
result['category'] = category
result['category_url'] = category_url
result['relative_list'] = relative_list
except IndexError or KeyError: # 网页改版的情况
return BaseHandler().write_error()
return BaseHandler().write_object(code=const.SUCCESS_CODE,
message=const.SUCCESS_MESSAGE,
result=result)
def __get_recommend_bangumi(self):
url = 'http://bangumi.bilibili.com/web_api/season/recommend/{sid}.json'.format(
sid=self.sid)
res = requests.get(url)
if 304 >= res.status_code >= 200:
loads = json.loads(res.text)
return loads['result']['list']
return BaseHandler().write_error()
def get_data(self):
url = 'http://www.bilibili.com/video/av%s/' % self.aid
res = requests.get(url, allow_redirects=True)
history = res.history
if len(history) == 0:
return self.__filter_normal_video(res.text)
elif len(history) > 0: # 出现重定向
return self.__filter_bangumi_video(res.text)
return BaseHandler().write_error()
def __get_first_data(self, url):
# 有banner | recommend 4 | 各个二级分类 12
'''
一级分类中的各个二级分类接口:http://api.bilibili.com/typedynamic/region
参数: rid --> 二级分类id | pn --> page num | ps --> 当月第几天
建两张表
'''
result = {}
res = requests.get(url)
if 304 >= res.status_code >= 200:
try:
soup = BeautifulSoup(res.text, 'lxml')
top_list = self.__get_top_list(self.first_tid)
result['banner'] = top_list
return BaseHandler().write_object(result=result)
except IndexError and KeyError:
return BaseHandler().write_error()
return BaseHandler().write_error()
def get_data(self):
url = 'http://bangumi.bilibili.com/jsonp/seasoninfo/{sid}.ver'.format(
sid=self.sid)
params = {'callback': 'seasonListCallback'}
res = requests.get(url, params=params)
if 304 >= res.status_code >= 200:
try:
result = json.loads(
res.text.replace('seasonListCallback(',
'').replace('});', '}'))['result']
recommend_bangumi = self.__get_recommend_bangumi()
result['recommend_bangumi'] = recommend_bangumi
return BaseHandler().write_object(
code=const.SUCCESS_CODE,
message=const.SUCCESS_MESSAGE,
result=result)
except KeyError:
return BaseHandler().write_error(400, '协议错误')
return BaseHandler().write_error()
def get_category(self):
url = 'http://www.bilibili.com'
res = requests.get(url)
if 304 >= res.status_code >= 200:
soup = BeautifulSoup(res.text, 'lxml')
data = []
for item in soup.select('.nav-menu > li'):
child = []
for i_item in item.select('.i_num > li'):
title = i_item.select('a > b')[0].get_text()
url = i_item.select('a')[0]['href']
url = 'http:' + url if url.startswith('//') else url
L = dict([('second_name', title), ('second_url', url)])
child.append(L)
first_url = item.select('a')[0]['href']
first_url = 'http:' + first_url if first_url.startswith('//') else first_url
first_name = item.select('em')[0].get_text()
L = dict([('first_name', first_name), ('first_url', first_url), ('child', child)])
data.append(L)
return BaseHandler().write_object(result={'data': data})
return BaseHandler().write_error()
def get_category_video(self):
# 先拿当前的分类表 --> 再去匹配链接
video_list = []
category_table = json.loads(self.get_category())
if self.first_tid is None:
return video_list
for first_item in category_table:
if self.first_tid == first_item:
if self.second_tid is None:
url = category_table[first_item]['normal']
return self.__get_first_data(url=url)
for second_item in first_item:
if self.second_tid == second_item:
url = category_table[first_item][second_item]
return self.__get_second_data(url=url)
# 匹配不到第二层分类的情况,有可能为空或没有这个分类
return BaseHandler().write_error()
def __filter(self, json_data):
json_data = str(json_data).replace('callback(', '').replace('});', '}')
json_data = json.loads(json_data)['data']['recommend']
return BaseHandler().write_list(const.SUCCESS_CODE,
const.SUCCESS_MESSAGE, len(json_data),
json_data)
def get_live(self):
res = requests.get(url=self.url, params=self.params)
if 304 >= res.status_code >= 200:
return self.__filter(res.text)
return BaseHandler().write_error()
def __filter_bangumi_video(self, data):
# todo 获取番剧视频详情信息
result = {}
return BaseHandler().write_object(code=const.SUCCESS_CODE,
message=const.SUCCESS_MESSAGE,
result=result)