async def owllook_add_book(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 添加书架失败
: 1 添加书架成功
"""
user = request['session'].get('user', None)
data = parse_qs(str(request.body, encoding='utf-8'))
novels_name = data.get('novels_name', '')
chapter_url = data.get('chapter_url', '')
last_read_url = data.get('last_read_url', '')
if user and novels_name and chapter_url:
url = "/chapter?url={chapter_url}&novels_name={novels_name}".format(chapter_url=chapter_url[0],
novels_name=novels_name[0])
time = get_time()
try:
motor_db = MotorBase().db
res = await motor_db.user_message.update_one({'user': user}, {'$set': {'last_update_time': time}},
upsert=True)
if res:
await motor_db.user_message.update_one(
{'user': user, 'books_url.book_url': {'$ne': url}},
{'$push': {
'books_url': {'book_url': url, 'add_time': time, 'last_read_url': unquote(last_read_url[0])}}})
LOGGER.info('书架添加成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def owl_novels_chapters(request):
"""
返回章节目录 基本达到通用
:param request:
:param chapter_url: 章节源目录页url
:param novels_name: 小说名称
:return: 小说目录信息
"""
chapters_url = request.args.get('chapters_url', None)
novels_name = request.args.get('novels_name', None)
netloc = get_netloc(chapters_url)
try:
res = await cache_owllook_novels_chapter(url=chapters_url,
netloc=netloc)
chapters_sorted = []
if res:
chapters_sorted = extract_chapters(chapters_url, res)
result = {'status': 200}
else:
result = {'status': 204}
result.update({
'data': {
'novels_name': novels_name,
'chapter_url': chapters_url,
'all_chapters': chapters_sorted
},
'msg': "ok"
})
except Exception as e:
LOGGER.exception(e)
result = {'status': 500, 'msg': e}
result.update({'finished_at': get_time()})
return response.json(result)
async def owllook_add_bookmark(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 添加书签失败
: 1 添加书签成功
"""
user = request['session'].get('user', None)
data = parse_qs(str(request.body, encoding='utf-8'))
bookmarkurl = data.get('bookmarkurl', '')
if user and bookmarkurl:
url = unquote(bookmarkurl[0])
time = get_time()
try:
motor_db = MotorBase().db
res = await motor_db.user_message.update_one({'user': user}, {'$set': {'last_update_time': time}},
upsert=True)
if res:
await motor_db.user_message.update_one(
{'user': user, 'bookmarks.bookmark': {'$ne': url}},
{'$push': {'bookmarks': {'bookmark': url, 'add_time': time}}})
LOGGER.info('书签添加成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def get_tag():
motor_db = MotorBase().get_db()
novels = Novels()
# 获取所有书架链接游标
books_url_cursor = motor_db.user_message.find({}, {'books_url.book_url': 1, 'user': 1, '_id': 0})
async for document in books_url_cursor:
if document:
books_url = document.get('books_url', None)
if books_url:
all_user = {}
user = document['user']
all_user[user + '_novels'] = []
all_user[user + '_tag'] = []
all_user[user + '_author'] = []
for book_url in books_url:
chapter_url = book_url['book_url']
novels_name = parse_qs(urlparse(chapter_url).query).get('novels_name', '')[0]
all_user[user + '_novels'].append(novels_name)
novels_info = novels.search_name(novels_name)
if novels_info:
novels_type = novels_info['novels_type'].split('#')
author = novels_info['author']
all_user[user + '_author'].append(author)
all_user[user + '_tag'].extend(novels_type)
data = {
'user_novels': all_user[user + '_novels'],
'user_tag': all_user[user + '_tag'],
'user_author': all_user[user + '_author'],
}
await motor_db.user_tag.update_one(
{"user": user},
{'$set': {'data': data, "updated_at": get_time()}}, upsert=True)
pprint(data)
async def owl_novels_chapters(request, **kwargs):
"""
返回章节目录 基本达到通用
:param request:
:param chapter_url: 章节源目录页url
:param novels_name: 小说名称
:return: 小说目录信息
"""
request_params = kwargs["request_params"]
chapters_url = request_params.get('chapters_url', None)
novels_name = request_params.get('novels_name', None)
netloc = get_netloc(chapters_url)
try:
res = await cache_owllook_novels_chapter(url=chapters_url, netloc=netloc)
chapters_sorted = []
if res:
chapters_sorted = extract_chapters(chapters_url, res)
UniResponse.SUCCESS.update({ResponseField.DATA: {
'novels_name': novels_name,
'chapter_url': chapters_url,
'all_chapters': chapters_sorted
}, ResponseField.FINISH_AT: get_time()})
return response_handle(request, UniResponse.SUCCESS, 200)
except Exception as e:
LOGGER.exception(e)
return response_handle(request, UniResponse.SERVER_UNKNOWN_ERR, 500)
async def get_user_tag():
motor_db = MotorBase().get_db()
user_tag_cursor = motor_db.user_tag.find({}, {
'data.user_tag': 1,
'user': 1,
'_id': 0
})
result = {}
async for document in user_tag_cursor:
if document['data']['user_tag']:
result[document['user'].replace(
'.', '·')] = document['data']['user_tag']
for key, value in result.items():
result_copy = deepcopy(result)
del result_copy[key]
cos = CosineSimilarity(value, result_copy)
vector = cos.create_vector()
resultDic = cos.calculate(vector)
pprint(resultDic)
# pprint(type(resultList[1]))
await motor_db.user_recommend.update_one({"user": key}, {
'$set': {
'similar_user': resultDic,
'user_tag': result[key],
"updated_at": get_time()
}
},
upsert=True)
async def get_user_tag():
motor_db = MotorBase().get_db()
user_tag_cursor = motor_db.user_tag.find({}, {
'data': 1,
'user': 1,
'_id': 0
})
result = {}
user_book_dict = {}
async for document in user_tag_cursor:
if document['data']:
user_book_dict[document['user'].replace(
'.', '·')] = document['data']
result[document['user'].replace(
'.', '·')] = document['data']['user_tag']
for key, value in result.items():
if not value:
continue
print("\nUser:"******"User tags:", set(value))
print("User books:", user_book_dict[key]["user_novels"])
result_copy = deepcopy(result)
del result_copy[key]
cos = CosineSimilarity(value, result_copy)
vector = cos.create_vector()
resultDic = cos.calculate(vector)
print("相似用户:")
pprint(resultDic[:10])
# pprint(type(resultList[1]))
booksDic = collections.defaultdict(float)
for userBooks in resultDic:
for simuser, simrate in userBooks.items():
# print(simuser, simrate)
for book in user_book_dict[simuser]["user_novels"]:
booksDic[book] += simrate
# print(booksDic)
# 推荐20本书，注意这里的推荐并没有去除用户收藏的书籍
recommend = sorted(booksDic.items(), key=itemgetter(1),
reverse=True)[0:20]
print("书籍推荐：")
pprint(recommend)
recommend_novels = [book for book, simrate in recommend]
await motor_db.user_recommend.update_one({"user": key}, {
'$set': {
'similar_user': resultDic,
'user_tag': result[key],
'recommend_novels': recommend_novels,
"updated_at": get_time()
}
},
upsert=True)
async def owllook_register(request):
"""
用户注册 不允许重名
:param request:
:return:
: -1 用户名已存在
: 0 用户名或密码不能为空
: 1 注册成功
"""
register_data = parse_qs(str(request.body, encoding='utf-8'))
user = register_data.get('user', [None])[0]
pwd = register_data.get('pwd', [None])[0]
email = register_data.get('email', [None])[0]
answer = register_data.get('answer', [None])[0]
reg_index = request.cookies.get('reg_index')
if user and pwd and email and answer and reg_index and len(
user) > 2 and len(pwd) > 5:
motor_db = motor_base.get_db()
is_exist = await motor_db.user.find_one({'user': user})
if not is_exist:
# 验证问题答案是否准确
real_answer = get_real_answer(str(reg_index))
if real_answer and real_answer == answer:
pass_first = hashlib.md5((CONFIG.WEBSITE["TOKEN"] +
pwd).encode("utf-8")).hexdigest()
password = hashlib.md5(pass_first.encode("utf-8")).hexdigest()
time = get_time()
data = {
"user": user,
"password": password,
"email": email,
"register_time": time,
}
await motor_db.user.insert_one(data)
return json({'status': 1})
else:
return json({'status': -2})
else:
return json({'status': -1})
else:
return json({'status': 0})
async def owl_so_novels(request, name):
"""
360小说信息接口
:param request:
:param name: 小说名
:return: 小说相关信息
"""
name = unquote(name)
novels_name = '{name} 小说 免费阅读'.format(name=name)
try:
res = await cache_owllook_so_novels_result(novels_name)
parse_result = None
if res:
parse_result = [i for i in res if i]
result = {'status': 200}
else:
result = {'status': 204}
result.update({'data': parse_result, 'msg': "ok"})
except Exception as e:
LOGGER.exception(e)
result = {'status': 500, 'msg': e}
result.update({'finished_at': get_time()})
return response.json(result)
async def owl_so_novels(request, name):
"""
360小说信息接口
:param request:
:param name: 小说名
:return: 小说相关信息
"""
name = unquote(name)
novels_name = '{name} 小说 免费阅读'.format(name=name)
try:
res = await get_novels_info(class_name='baidu',
novels_name=novels_name)
parse_result = []
if res:
parse_result = [i for i in res if i]
UniResponse.SUCCESS.update({
ResponseField.DATA: parse_result,
ResponseField.FINISH_AT: get_time()
})
return response_handle(request, UniResponse.SUCCESS, 200)
except Exception as e:
LOGGER.exception(e)
return response_handle(request, UniResponse.SERVER_UNKNOWN_ERR, 500)
async def get_the_latest_chapter(chapter_url, loop=None, timeout=15):
try:
with async_timeout.timeout(timeout):
url = parse_qs(urlparse(chapter_url).query).get('url', '')
novels_name = parse_qs(urlparse(chapter_url).query).get(
'novels_name', '')
data = None
if url and novels_name:
url = url[0]
novels_name = novels_name[0]
netloc = urlparse(url).netloc
if netloc in LATEST_RULES.keys():
async with aiohttp.ClientSession(loop=loop) as client:
headers = {'user-agent': await get_random_user_agent()}
try:
html = await target_fetch(client=client,
url=url,
headers=headers,
timeout=timeout)
if html is None:
html = get_html_by_requests(url=url,
headers=headers,
timeout=timeout)
except TypeError:
html = get_html_by_requests(url=url,
headers=headers,
timeout=timeout)
except Exception as e:
LOGGER.exception(e)
return None
try:
soup = BeautifulSoup(html, 'html5lib')
except Exception as e:
LOGGER.exception(e)
return None
latest_chapter_name, latest_chapter_url = None, None
if LATEST_RULES[netloc].plan:
meta_value = LATEST_RULES[netloc].meta_value
latest_chapter_name = soup.select(
'meta[property="{0}"]'.format(
meta_value["latest_chapter_name"]))
latest_chapter_name = latest_chapter_name[0].get(
'content',
None) if latest_chapter_name else None
latest_chapter_url = soup.select(
'meta[property="{0}"]'.format(
meta_value["latest_chapter_url"]))
latest_chapter_url = urljoin(
url, latest_chapter_url[0].get(
'content',
None)) if latest_chapter_url else None
else:
selector = LATEST_RULES[netloc].selector
content_url = selector.get('content_url')
if selector.get('id', None):
latest_chapter_soup = soup.find_all(
id=selector['id'])
elif selector.get('class', None):
latest_chapter_soup = soup.find_all(
class_=selector['class'])
else:
latest_chapter_soup = soup.select(
selector.get('tag'))
if latest_chapter_soup:
if content_url == '1':
# TODO
pass
elif content_url == '0':
# TODO
pass
else:
latest_chapter_url = content_url + latest_chapter_soup[
0].get('href', None)
latest_chapter_name = latest_chapter_soup[
0].get('title', None)
if latest_chapter_name and latest_chapter_url:
time_current = get_time()
# print(latest_chapter_url)
data = {
"latest_chapter_name":
latest_chapter_name,
"latest_chapter_url":
latest_chapter_url,
"owllook_chapter_url":
chapter_url,
"owllook_content_url":
"/owllook_content?url={latest_chapter_url}&name={name}&chapter_url={chapter_url}&novels_name={novels_name}"
.format(
latest_chapter_url=latest_chapter_url,
name=latest_chapter_name,
chapter_url=url,
novels_name=novels_name,
),
}
# 存储最新章节
motor_db = MotorBase().get_db()
await motor_db.latest_chapter.update_one(
{
"novels_name": novels_name,
'owllook_chapter_url': chapter_url
}, {
'$set': {
'data': data,
"finished_at": time_current
}
},
upsert=True)
return data
except Exception as e:
LOGGER.exception(e)
return None
async def author_notification(request):
"""
作者新书通知
:param request:
:return:
: -1 用户session失效 需要重新登录
: 2 无该作者信息
: 3 作者已经添加
: 4 超过添加的上限
: 0 操作失败
: 1 操作成功
"""
user = request['session'].get('user', None)
user_data = parse_qs(str(request.body, encoding='utf-8'))
if user:
try:
motor_db = motor_base.get_db()
all_authors = await motor_db.user_message.find_one(
{'user': user}, {
'author_latest': 1,
'_id': 0
})
count = len(all_authors.get('author_latest', []))
if count == CONFIG.WEBSITE.get("AUTHOR_LATEST_COUNT", 5):
return json({'status': 4})
author_name = user_data.get('author_name', None)[0]
data = []
author_cursor = motor_db.all_books.find({'author': author_name}, {
'name': 1,
'url': 1,
'_id': 0
})
async for document in author_cursor:
data.append(document)
if data:
time = get_time()
res = await motor_db.user_message.update_one(
{'user': user}, {'$set': {
'last_update_time': time
}},
upsert=True)
is_exist = await motor_db.user_message.find_one({
'user':
user,
'author_latest.author_name':
author_name
})
if is_exist:
return json({'status': 3})
if res:
await motor_db.user_message.update_one(
{
'user': user,
'author_latest.author_name': {
'$ne': author_name
}
}, {
'$push': {
'author_latest': {
'author_name': author_name,
'add_time': time
}
}
})
is_author_exist = await motor_db.author_message.find_one(
{'name': author_name})
if not is_author_exist:
author_data = {
"author_name": author_name,
"nums": len(data),
"updated_time": get_time(),
}
await motor_db.author_message.save(author_data)
LOGGER.info('作者添加成功')
return json({'status': 1})
else:
return json({'status': 2})
else:
return json({'status': 2})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def owllook_search(request):
start = time.time()
name = str(request.args.get('wd', '')).strip()
novels_keyword = name.split(' ')[0]
motor_db = motor_base.get_db()
if not name:
return redirect('/')
else:
# 记录搜索小说名
try:
await motor_db.search_records.update_one({'keyword': name}, {'$inc': {'count': 1}}, upsert=True)
except Exception as e:
LOGGER.exception(e)
# 通过搜索引擎获取检索结果
parse_result = None
if name.startswith('!baidu'):
novels_keyword = name.split('baidu')[1].strip()
novels_name = 'intitle:{name} 小说 阅读'.format(name=novels_keyword)
parse_result = await cache_owllook_baidu_novels_result(novels_name)
elif name.startswith('!360'):
novels_keyword = name.split('360')[1].strip()
novels_name = "{name} 小说 最新章节".format(name=novels_keyword)
parse_result = await cache_owllook_so_novels_result(novels_name)
elif name.startswith('!bing'):
novels_keyword = name.split('bing')[1].strip()
novels_name = "{name} 小说 阅读 最新章节".format(name=novels_keyword)
parse_result = await cache_owllook_bing_novels_result(novels_name)
# elif name.startswith('!duck_go'):
# novels_keyword = name.split('duck_go')[1].strip()
# novels_name = '{name} 小说 阅读 最新章节'.format(name=novels_keyword)
# parse_result = await cache_owllook_duck_novels_result(novels_name)
else:
for each_engine in ENGINE_PRIORITY:
# for bing
if each_engine == "bing":
novels_name = "{name} 小说 阅读 最新章节".format(name=name)
parse_result = await cache_owllook_bing_novels_result(novels_name)
if parse_result:
break
# for 360 so
if each_engine == "360":
novels_name = "{name} 小说 最新章节".format(name=name)
parse_result = await cache_owllook_so_novels_result(novels_name)
if parse_result:
break
# for baidu
if each_engine == "baidu":
novels_name = 'intitle:{name} 小说 阅读'.format(name=name)
parse_result = await cache_owllook_baidu_novels_result(novels_name)
if parse_result:
break
# for duckduckgo
if each_engine == "duck_go":
novels_name = '{name} 小说 阅读 最新章节'.format(name=name)
parse_result = await cache_owllook_duck_novels_result(novels_name)
if parse_result:
break
if parse_result:
# result_sorted = sorted(
# parse_result, reverse=True, key=lambda res: res['timestamp']) if ':baidu' not in name else parse_result
# 优先依靠是否解析进行排序 其次以更新时间进行排序
result_sorted = sorted(
parse_result,
reverse=True,
key=itemgetter('is_recommend', 'is_parse', 'timestamp'))
user = request['session'].get('user', None)
if user:
try:
time_current = get_time()
res = await motor_db.user_message.update_one({'user': user},
{'$set': {'last_update_time': time_current}},
upsert=True)
# 此处语法操作过多 下次看一遍mongo再改
if res:
is_ok = await motor_db.user_message.update_one(
{'user': user, 'search_records.keyword': {'$ne': novels_keyword}},
{'$push': {'search_records': {'keyword': novels_keyword, 'counts': 1}}},
)
if is_ok:
await motor_db.user_message.update_one(
{'user': user, 'search_records.keyword': novels_keyword},
{'$inc': {'search_records.$.counts': 1}}
)
except Exception as e:
LOGGER.exception(e)
return template(
'result.html',
is_login=1,
user=user,
name=novels_keyword,
time='%.2f' % (time.time() - start),
result=result_sorted,
count=len(parse_result))
else:
return template(
'result.html',
is_login=0,
name=novels_keyword,
time='%.2f' % (time.time() - start),
result=result_sorted,
count=len(parse_result))
else:
return html("No Result！请将小说名反馈给本站，谢谢！")
async def owl_bd_novels(request, name):
"""
百度小说信息接口
:param request:
:param name: 小说名
:return: 小说相关信息
"""
name = unquote(name)
novels_name = 'intitle:{name} 小说 阅读'.format(name=name)
try:
res = await cache_owllook_baidu_novels_result(novels_name)
parse_result = []
if res:
parse_result = [i for i in res if i]
UniResponse.SUCCESS.update({ResponseField.DATA: parse_result, ResponseField.FINISH_AT: get_time()})
return response_handle(request, UniResponse.SUCCESS, 200)
except Exception as e:
LOGGER.exception(e)
return response_handle(request, UniResponse.SERVER_UNKNOWN_ERR, 500)
async def get_the_latest_chapter(chapter_url):
url = parse_qs(urlparse(chapter_url).query).get('url', '')
novels_name = parse_qs(urlparse(chapter_url).query).get('novels_name', '')
data = None
if url and novels_name:
url = url[0]
novels_name = novels_name[0]
netloc = urlparse(url).netloc
if netloc in LATEST_RULES.keys():
async with aiohttp.ClientSession() as client:
html = await target_fetch(client=client, url=url)
soup = BeautifulSoup(html, 'html5lib')
latest_chapter_name, latest_chapter_url = None, None
if LATEST_RULES[netloc].plan:
meta_value = LATEST_RULES[netloc].meta_value
latest_chapter_name = soup.select(
'meta[property="{0}"]'.format(
meta_value["latest_chapter_name"]))
latest_chapter_name = latest_chapter_name[0].get(
'content', None) if latest_chapter_name else None
latest_chapter_url = soup.select(
'meta[property="{0}"]'.format(
meta_value["latest_chapter_url"]))
latest_chapter_url = latest_chapter_url[0].get(
'content', None) if latest_chapter_url else None
else:
selector = LATEST_RULES[netloc].selector
content_url = selector.get('content_url')
if selector.get('id', None):
latest_chapter_soup = soup.find_all(id=selector['id'])
elif selector.get('class', None):
latest_chapter_soup = soup.find_all(
class_=selector['class'])
else:
latest_chapter_soup = soup.select(selector.get('tag'))
if latest_chapter_soup:
if content_url == '1':
# TODO
pass
elif content_url == '0':
# TODO
pass
else:
latest_chapter_url = content_url + latest_chapter_soup[
0].get('href', None)
latest_chapter_name = latest_chapter_soup[0].get(
'title', None)
if latest_chapter_name and latest_chapter_url:
time_current = get_time()
data = {
"latest_chapter_name":
latest_chapter_name,
"latest_chapter_url":
latest_chapter_url,
"owllook_chapter_url":
chapter_url,
"owllook_content_url":
"/owllook_content?url={latest_chapter_url}&name={name}&chapter_url={chapter_url}&novels_name={novels_name}"
.format(
latest_chapter_url=latest_chapter_url,
name=latest_chapter_name,
chapter_url=url,
novels_name=novels_name,
),
}
# 存储最新章节
motor_db = MotorBase().db
await motor_db.latest_chapter.update_one(
{
"novels_name": novels_name,
'owllook_chapter_url': chapter_url
},
{'$set': {
'data': data,
"finished_at": time_current
}},
upsert=True)
return data
