r = await self.async_crawl(url)
if not r:
return False
dom = pq(r.content.decode())
now_pt = int(dom('span.price').text())
oepn_pt = int(dom('.idx-data-pri > li > b.i').eq(0).text())
high_pt = int(dom('.idx-data-pri > li > b.i').eq(1).text())
low_pt = int(dom('.idx-data-pri > li > b.i').eq(2).text())
if (now_pt >= self.high_limit or now_pt <= self.low_limit) and \
self.high_limit and self.low_limit:
logger.warning('open: %s high: %s low: %s close: %s !!!!!!!!', oepn_pt, high_pt, low_pt, now_pt)
else:
logger.info('open: %s high: %s low: %s close: %s', oepn_pt, high_pt, low_pt, now_pt)
return True
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("-l", "--low", help="low", type=int, default=0)
parser.add_argument("-g", "--high", help="high", type=int, default=0)
args = parser.parse_args()
log.initlog('DEMO', level=logging.INFO, debug=True)
c = Crawler()
high_limit = 10450
low_limit = 10430
c.sleep_time = 30
c.low_limit = int(low_limit)
c.high_limit = int(high_limit)
c.run()
content=content
)
# articles.insert(ret)
async def login(self):
url = 'http://www.huntcoco.com/member/account_login1.php'
r = await self.async_crawl(url, method='POST', headers="""
Accept: */*
Accept-Encoding: gzip, deflate
Accept-Language: zh-TW,zh;q=0.9,en;q=0.8,zh-CN;q=0.7,en-US;q=0.6
Cache-Control: no-cache
Connection: keep-alive
Content-Length: 46
Content-Type: application/x-www-form-urlencoded; charset=UTF-8
Host: www.huntcoco.com
Origin: http://www.huntcoco.com
Pragma: no-cache
Referer: http://www.huntcoco.com/index.php?goto=41
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36
X-Requested-With: XMLHttpRequest
""", data=headers_raw_to_dict("""
a: [email protected]
b: ji394su3
"""))
if __name__ == '__main__':
log.initlog('DEMO', level=logging.DEBUG, debug=True)
c = Crawler()
c.run()
content=content,
url=item["alternate"][0]["href"],
category=category,
)
self.datas.append(dct)
print(item["title"], dct["url"])
def get_api(self, stream_id, continuation=None):
api = "https://feedly.com/v3/streams/contents"
ts = str(time.time()).replace(".", "")[:13]
params = headers_raw_to_dict("""
streamId: {}
count: 40
unreadOnly: true
ranked: newest
similar: true
ck: {}
ct: feedly.desktop
cv: 31.0.269
continuation: {}
""".format(stream_id, ts, continuation))
if not params["continuation"]:
del params["continuation"]
return url_add_params(api, **params)
if __name__ == "__main__":
log.initlog("DEMO", level=logging.DEBUG, debug=True)
c = Crawler()
c.run()