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 = OrderedDict()
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>)'
judge_reg = r'^[上前下后][一]?[页张个篇章节步]$'
# 这里同样需要利用bs再次解析
next_res = re.findall(next_reg, html, re.I)
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.replace(' ', '')
is_next = re.search(judge_reg, text)
# is_ok = is_chapter(text)
if is_next:
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 next_chapter
except Exception as e:
LOGGER.exception(e)
return next_chapter
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 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))
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 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 data_extraction_for_web_baidu(client, html):
with async_timeout.timeout(20):
try:
# 获取一段h5
url = html.select('h3.t a')[0].get('href', None)
# 获取href标签内容 -
# 首先 - html.select('h3.t a')[0]
# < a
# data - click = "{
# 'F': '778317EA',
# 'F1': '9D73F1E4',
# 'F2': '4DA6DD6B',
# 'F3': '54E5363F',
# 'T': '1497109660',
# 'y': 'A7BFAFBF'
#
# }" href="
# http: // www.baidu.com / link?url = w2bV3ST9FFL3f39PGG6VUhT10aqZ1GNZrhWa5BIclVak7hYZEh1wGiTsvrGYJgXJEAPNoPfS7x0X4xK9nLDzJK
# " target="
# _blank
# "><em>择天记</em>,<em>择天记</em>最新章节,<em>择天记</em>无弹窗,88读书网</a>
# 然后 - get('href', None)
# http: // www.baidu.com / link?url = w2bV3ST9FFL3f39PGG6VUhT10aqZ1GNZrhWa5BIclVak7hYZEh1wGiTsvrGYJgXJEAPNoPfS7x0X4xK9nLDzJK
real_url = await get_real_url(client=client,
url=url) if url else None
if real_url:
netloc = urlparse(str(real_url)).netloc
# >> > import urlparse
# >> > url = urlparse.urlparse('http://www.baidu.com/index.php?username=guol')
# >> > print
# url
# ParseResult(scheme='http', netloc='www.baidu.com', path='/index.php', params='', query='username=guol',
# fragment='')
# >> > print
# url.netloc
# www.baidu.com
if 'baidu' in str(real_url) or netloc in BLACK_DOMAIN:
return None
#print('--------------------')
#print(RULES.keys())
is_parse = 1 if netloc in RULES.keys() else 0
title = html.select('h3.t a')[0].get_text()
# 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': str(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
kl = kube_listener(EVENT_MESSAGE_TEMPLATE, CURRENT_NAMESPACE, SLACK_URL,
LOGGER)
app = Flask(__name__)
app.debug = True
@app.route('/api/v1/events/<type>', methods=['GET'])
def api_get_events_json(type):
if request.method == 'GET':
if type == 'json':
event_table = kl.get_dictionary()
return jsonify(event_table)
else:
return ("Method not supported.", 400)
startup_time = str(datetime.datetime.now())
LOGGER.info("{}".format(STARTUP_INFORMATION_MESSAGE))
startup_information_message = STARTUP_INFORMATION_MESSAGE % (CURRENT_NAMESPACE,
startup_time)
r = requests.post(SLACK_URL, data=startup_information_message)
LOGGER.info("POST request result from slack: {} {}".format(
r.status_code, r.reason))
if __name__ == "__main__":
kl.start()
app.run(host="0.0.0.0", port=5000)
kl.join()