async def data_extraction_for_web_baidu(client, html):
with async_timeout.timeout(20):
try:
url = html.select('h3.t a')[0].get('href', None)
real_url = await get_real_url(client=client, url=url) if url else None
if real_url:
netloc = urlparse(real_url).netloc
if 'baidu' in real_url or netloc in BLACK_DOMAIN:
return None
is_parse = 1 if netloc in RULES.keys() else 0
title = html.select('h3.t a')[0].get_text()
source = real_url
# time = re.findall(r'\d+-\d+-\d+', source)
# time = time[0] if time else None
timestamp = 0
time = ""
# if time:
# try:
# time_list = [int(i) for i in time.split('-')]
# timestamp = arrow.get(time_list[0], time_list[1], time_list[2]).timestamp
# except Exception as e:
# LOGGER.exception(e)
# timestamp = 0
return {'title': title, 'url': real_url.replace('index.html', ''), 'time': time, 'is_parse': is_parse,
'timestamp': timestamp,
'netloc': netloc}
else:
return None
except Exception as e:
LOGGER.exception(e)
return None
async def owllook_delete_bookmark(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 删除书签失败
: 1 删除书签成功
"""
user = request['session'].get('user', None)
data = parse_qs(str(request.body, encoding='utf-8'))
bookmarkurl = data.get('bookmarkurl', '')
if user and bookmarkurl:
bookmark = unquote(bookmarkurl[0])
try:
motor_db = MotorBase().db
await motor_db.user_message.update_one(
{'user': user},
{'$pull': {
'bookmarks': {
"bookmark": bookmark
}
}})
LOGGER.info('删除书签成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def owllook_delete_bookmark(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 删除书签失败
: 1 删除书签成功
"""
user = request['session'].get('user', None)
if user:
bookmarkurl = request.args.get('bookmarkurl', '')
name = request.args.get('name', '')
chapter_url = request.args.get('chapter_url', '')
novels_name = request.args.get('novels_name', '')
url = bookmarkurl + "&name=" + name + "&chapter_url=" + chapter_url + "&novels_name=" + novels_name
try:
motor_db = MotorBase().db
motor_db.user_message.update_one(
{'user': user}, {'$pull': {
'bookmarks': {
"bookmark": url
}
}})
LOGGER.info('删除书签成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def owllook_delete_book(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 删除书架失败
: 1 删除书架成功
"""
user = request['session'].get('user', None)
data = parse_qs(str(request.body, encoding='utf-8'))
if user:
if data.get('book_url', None):
book_url = data.get('book_url', None)[0]
else:
novels_name = data.get('novels_name', '')
chapter_url = data.get('chapter_url', '')
book_url = "/chapter?url={chapter_url}&novels_name={novels_name}".format(
chapter_url=chapter_url[0], novels_name=novels_name[0])
try:
motor_db = MotorBase().db
await motor_db.user_message.update_one(
{'user': user},
{'$pull': {
'books_url': {
"book_url": unquote(book_url)
}
}})
LOGGER.info('删除书架成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
def extract_pre_next_chapter(chapter_url, html):
"""
获取单章节上一页下一页
:param chapter_url:
:param html:
:return:
"""
next_chapter = {}
try:
# 参考https://greasyfork.org/zh-CN/scripts/292-my-novel-reader
next_reg = r'(<a\s+.*?>.*[上前下后][一]?[页张个篇章节步].*?</a>)'
# 这里同样需要利用bs再次解析
next_res = re.findall(next_reg, html)
str_next_res = '\n'.join(next_res)
next_res_soup = BeautifulSoup(str_next_res, 'html5lib')
for link in next_res_soup.find_all('a'):
text = link.text or ''
text = text.strip().replace(' ', '')
is_ok = is_chapter(text)
if is_ok:
url = urljoin(chapter_url, link.get('href')) or ''
next_chapter[text] = url
nextDic = [{v[0]: v[1]} for v in sorted(next_chapter.items(), key=lambda d: d[1])]
return nextDic
except Exception as e:
LOGGER.exception(e)
return next_chapter
async def data_extraction_for_web_so(client, html):
with async_timeout.timeout(15):
try:
try:
url = html.select('h3.res-title a')[0].get('href', None)
title = html.select('h3.res-title a')[0].get_text()
except IndexError:
url = html.select('h3.title a')[0].get('href', None)
title = html.select('h3.title a')[0].get_text()
except Exception as e:
LOGGER.exception(e)
url, title = None, None
url = parse_qs(urlparse(url).query).get('url', None)
url = url[0] if url else None
netloc = urlparse(url).netloc
if not url or 'baidu' in url or 'baike.so.com' in url or netloc in BLACK_DOMAIN:
return None
is_parse = 1 if netloc in RULES.keys() else 0
time = ''
timestamp = 0
return {
'title': title,
'url': url.replace('index.html', ''),
'time': time,
'is_parse': is_parse,
'timestamp': timestamp,
'netloc': netloc
}
except Exception as e:
LOGGER.exception(e)
return None
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 fetch(client, url, name, is_web):
with async_timeout.timeout(15):
try:
headers = {'user-agent': get_random_user_agent()}
if is_web:
params = {
'wd': name,
'ie': 'utf-8',
'rn': BAIDU_RN,
'vf_bl': 1
}
else:
params = {'word': name}
async with client.get(url, params=params,
headers=headers) as response:
assert response.status == 200
LOGGER.info('Task url: {}'.format(response.url))
try:
text = await response.text()
except:
text = await response.read()
return text
except Exception as e:
LOGGER.exception(e)
return None
async def owllook_delete_book(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 删除书架失败
: 1 删除书架成功
"""
user = request['session'].get('user', None)
if user:
novels_name = request.args.get('novels_name', '')
chapter_url = request.args.get('chapter_url', '')
url = "/chapter?url={chapter_url}&novels_name={novels_name}".format(
chapter_url=chapter_url, novels_name=novels_name)
try:
motor_db = MotorBase().db
motor_db.user_message.update_one(
{'user': user}, {'$pull': {
'books_url': {
"book_url": url
}
}})
LOGGER.info('删除书架成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def data_extraction_for_web(html):
with async_timeout.timeout(10):
try:
url = html.find('a').get('href', None)
if not url or 'baidu' in url or urlparse(
url).netloc in BLACK_DOMAIN:
return None
netloc = urlparse(url).netloc
is_parse = 1 if netloc in RULES.keys() else 0
title = html.select('font[size="3"]')[0].get_text()
source = html.select('font[color="#008000"]')[0].get_text()
time = re.findall(r'\d+-\d+-\d+', source)
time = time[0] if time else None
timestamp = 0
if time:
try:
time_list = [int(i) for i in time.split('-')]
timestamp = arrow.get(time_list[0], time_list[1],
time_list[2]).timestamp
except Exception as e:
LOGGER.exception(e)
timestamp = 0
return {
'title': title,
'url': url.replace('index.html', '').replace('Index.html', ''),
'time': time,
'is_parse': is_parse,
'timestamp': timestamp,
'netloc': netloc
}
except Exception as e:
LOGGER.exception(e)
return None
async def fetch(client, url):
with async_timeout.timeout(10):
try:
headers = {'user-agent': get_random_user_agent()}
async with client.get(url, headers=headers) as response:
assert response.status == 200
LOGGER.info('Task url: {}'.format(response.url))
text = await response.text()
return text
except Exception as e:
LOGGER.exception(e)
return None
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
}
}, {
'$push': {
'books_url': {
'book_url': url,
'add_time': time,
'last_read_url': unquote(last_read_url[0])
}
}
})
LOGGER.info('书架添加成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def fetch(client, url, novels_name):
with async_timeout.timeout(15):
try:
headers = {'user-agent': get_random_user_agent()}
params = {'q': novels_name, 'ie': 'utf-8'}
async with client.get(url, params=params, headers=headers) as response:
assert response.status == 200
LOGGER.info('Task url: {}'.format(response.url))
try:
text = await response.text()
except:
text = await response.read()
return text
except Exception as e:
LOGGER.exception(e)
return None
async def data_extraction_for_phone(html):
with async_timeout.timeout(10):
try:
# Get title
data_log = eval(html['data-log'])
url = data_log.get('mu', None)
if not url:
return None
# Get title
title = html.find('h3').get_text()
# Get author and update_time (option)
novel_mess = html.findAll(class_='c-gap-right-large')
basic_mess = [i.get_text() for i in novel_mess] if novel_mess else None
return {'title': title, 'url': url, 'basic_mess': basic_mess}
except Exception as e:
LOGGER.exception(e)
return None
async def owllook_add_bookmark(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 添加书签失败
: 1 添加书签成功
"""
user = request['session'].get('user', None)
if user:
bookmarkurl = request.args.get('bookmarkurl', '')
name = request.args.get('name', '')
chapter_url = request.args.get('chapter_url', '')
novels_name = request.args.get('novels_name', '')
url = bookmarkurl + "&name=" + name + "&chapter_url=" + chapter_url + "&novels_name=" + novels_name
time = get_time()
try:
motor_db = MotorBase().db
res = motor_db.user_message.update_one(
{'user': user}, {'$set': {
'last_update_time': time
}},
upsert=True)
if res:
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 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)
if user:
novels_name = request.args.get('novels_name', '')
chapter_url = request.args.get('chapter_url', '')
url = "/chapter?url={chapter_url}&novels_name={novels_name}".format(
chapter_url=chapter_url, novels_name=novels_name)
time = get_time()
try:
motor_db = MotorBase().db
res = motor_db.user_message.update_one(
{'user': user}, {'$set': {
'last_update_time': time
}},
upsert=True)
if res:
motor_db.user_message.update_one(
{
'user': user,
'books_url.book_url': {
'$ne': url
}
}, {
'$push': {
'books_url': {
'book_url': url,
'add_time': time
}
}
})
LOGGER.info('书架添加成功')
return json({'status': 1})
except Exception as e:
LOGGER.exception(e)
return json({'status': 0})
else:
return json({'status': -1})
async def owllook_add_bookmark(request):
"""
:param request:
:return:
: -1 用户session失效 需要重新登录
: 0 添加书签失败
: 1 添加书签成功
"""
user = request['session'].get('user', None)
data = parse_qs(str(request.body, encoding='utf-8'))
bookmarkurl = data.get('bookmarkurl', '')
if user and bookmarkurl:
url = unquote(bookmarkurl[0])
time = get_time()
try:
motor_db = MotorBase().db
res = await motor_db.user_message.update_one(
{'user': user}, {'$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 owllook_search(request):
start = time.time()
name = request.args.get('wd', None)
if not name:
return redirect('/')
else:
novels_name = 'intitle:{name} 小说 阅读'.format(
name=name) if ':baidu' not in name else name.split('baidu')[1]
try:
motor_db = MotorBase().db
motor_db.search_records.update_one({'keyword': name},
{'$inc': {
'count': 1
}},
upsert=True)
except Exception as e:
LOGGER.exception(e)
is_web = int(request.args.get('is_web', 1))
result = await search(novels_name, is_web)
if result:
parse_result = [i for i in result if i]
result_sorted = sorted(
parse_result, reverse=True, key=lambda res: res[
'timestamp']) if ':baidu' not in name else parse_result
user = request['session'].get('user', None)
if user:
return template('result.html',
is_login=1,
user=user,
name=name,
time='%.2f' % (time.time() - start),
result=result_sorted,
count=len(parse_result))
else:
return template('result.html',
is_login=0,
name=name,
time='%.2f' % (time.time() - start),
result=result_sorted,
count=len(parse_result))
else:
return html("No Result!")
async def update_all_books():
try:
motor_db = MotorBase().db
# 获取所有书架链接游标
books_url_cursor = motor_db.user_message.find({}, {'books_url.book_url': 1, '_id': 0})
# 已更新url集合
already_urls = set()
async for document in books_url_cursor:
if document:
books_url = document['books_url']
# 一组书架链接列表数据
for book_url in books_url:
chapter_url = book_url['book_url']
if chapter_url not in already_urls:
await get_the_latest_chapter(chapter_url)
already_urls.add(chapter_url)
return True
except Exception as e:
LOGGER.exception(e)
return False
async def target_fetch(client, url):
"""
:param client: aiohttp client
:param url: targer url
:return: text
"""
with async_timeout.timeout(20):
try:
headers = {'user-agent': get_random_user_agent()}
async with client.get(url, headers=headers) as response:
assert response.status == 200
LOGGER.info('Task url: {}'.format(response.url))
try:
text = await response.text()
except:
text = await response.read()
return text
except Exception as e:
LOGGER.exception(e)
return None
async def get_real_url(client, url):
with async_timeout.timeout(10):
try:
headers = {'user-agent': get_random_user_agent()}
async with client.get(url, headers=headers, allow_redirects=True) as response:
assert response.status == 200
LOGGER.info('Parse url: {}'.format(response.url))
# text = ""
# try:
# text = await response.text()
# except:
# text = await response.read()
# if text:
# print(text)
# text = re.findall(r'replace\(\"(.*?)\"\)', str(text))
# text = text[0] if text[0] else ""
url = response.url if response.url else None
return url
except Exception as e:
LOGGER.exception(e)
return None
async def 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 request:
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 owllook_search(request):
start = time.time()
name = request.args.get('wd', None)
motor_db = MotorBase().db
if not name:
return redirect('/')
else:
# 记录搜索小说名
try:
await motor_db.search_records.update_one({'keyword': name},
{'$inc': {
'count': 1
}},
upsert=True)
except Exception as e:
LOGGER.exception(e)
# 通过搜索引擎获取检索结果
parse_result = [None]
for each_engine in ENGINE_PRIORITY:
# for 360 so
if each_engine == "360":
novels_name = "{name} 小说 免费阅读".format(name=name)
parse_result = await cache_owllook_so_novels_result(novels_name)
if parse_result:
break
if each_engine == "baidu":
# for baidu
novels_name = 'intitle:{name} 小说 阅读'.format(
name=name) if ':baidu' not in name else name.split('baidu')[1]
parse_result = await cache_owllook_baidu_novels_result(novels_name)
if parse_result:
break
if parse_result[0]:
# result_sorted = sorted(
# parse_result, reverse=True, key=lambda res: res['timestamp']) if ':baidu' not in name else parse_result
# 优先依靠是否解析进行排序 其次以更新时间进行排序
result_sorted = sorted(
parse_result,
reverse=True,
key=itemgetter(
'is_parse',
'timestamp')) if ':baidu' not in name else parse_result
user = request['session'].get('user', None)
if user:
try:
time_current = get_time()
res = await motor_db.user_message.update_one(
{'user': user},
{'$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': {
'$ne': name
}
},
{
'$push': {
'search_records': {
'keyword': name,
'counts': 1
}
}
},
)
if is_ok:
await motor_db.user_message.update_one(
{
'user': user,
'search_records.keyword': name
}, {'$inc': {
'search_records.$.counts': 1
}})
except Exception as e:
LOGGER.exception(e)
return template('result.html',
is_login=1,
user=user,
name=name,
time='%.2f' % (time.time() - start),
result=result_sorted,
count=len(parse_result))
else:
return template('result.html',
is_login=0,
name=name,
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 owllook_content(request):
"""
返回小说章节内容页
: content_url 这决定当前U页面url的生成方式
: url 章节内容页源url
: chapter_url 小说目录源url
: novels_name 小说名称
:return: 小说章节内容页
"""
url = request.args.get('url', None)
chapter_url = request.args.get('chapter_url', None)
novels_name = request.args.get('novels_name', None)
name = request.args.get('name', '')
# 当小说内容url不在解析规则内 跳转到原本url
netloc = get_netloc(url)
if netloc not in RULES.keys():
return redirect(url)
# 拼接小说目录url
book_url = "/chapter?url={chapter_url}&novels_name={novels_name}".format(
chapter_url=chapter_url, novels_name=novels_name)
if url == chapter_url:
return redirect(book_url)
content_url = RULES[netloc].content_url
content_data = await cache_owllook_novels_content(url=url, netloc=netloc)
if content_data:
user = request['session'].get('user', None)
try:
content = content_data.get('content', '获取失败')
next_chapter = content_data.get('next_chapter', '获取失败')
title = content_data.get('title', '获取失败')
name = name or title
# 拼接小说书签url
bookmark_url = "{path}?url={url}&name={name}&chapter_url={chapter_url}&novels_name={novels_name}".format(
path=request.path,
url=url,
name=name,
chapter_url=chapter_url,
novels_name=novels_name)
# 破坏广告链接
content = str(content).strip('[]Jjs,').replace('http', 'hs')
if user:
motor_db = MotorBase().db
bookmark = await motor_db.user_message.find_one({
'user':
user,
'bookmarks.bookmark':
bookmark_url
})
book = await motor_db.user_message.find_one({
'user':
user,
'books_url.book_url':
book_url
})
bookmark = 1 if bookmark else 0
if book:
# 当书架中存在该书源
book = 1
# 保存最后一次阅读记录
await motor_db.user_message.update_one(
{
'user': user,
'books_url.book_url': book_url
},
{'$set': {
'books_url.$.last_read_url': bookmark_url
}})
else:
book = 0
return template('content.html',
is_login=1,
user=user,
name=name,
url=url,
bookmark=bookmark,
book=book,
content_url=content_url,
chapter_url=chapter_url,
novels_name=novels_name,
next_chapter=next_chapter,
soup=content)
else:
return template('content.html',
is_login=0,
name=name,
url=url,
bookmark=0,
book=0,
content_url=content_url,
chapter_url=chapter_url,
novels_name=novels_name,
next_chapter=next_chapter,
soup=content)
except Exception as e:
LOGGER.exception(e)
return redirect(book_url)
else:
return text(
'解析失败或者是没有下一页了，请将失败页面反馈给本站，请重新刷新一次，或者访问源网页：{url}'.format(url=url))
