def rty(rows=None, **ka):
if not rows: rows = grows
rt = ''
dcol_range = {}
for k in py.list(ka):
for nc, c in py.enumerate(k):
if c in T._09:
i = py.int(c)
v = ka.pop(k)
if py.isnum(v):
dcol_range[i] = [v, U.IMAX]
elif py.istr(v):
if k[nc - 1] == '_':
dcol_range[-i] = v
else:
dcol_range[i] = v
elif py.len(v) == 2:
dcol_range[i] = v
else:
raise py.ArgumentError(' col range must int or [a,b] ')
break
if dcol_range:
print(' dcol_range:', dcol_range)
for index, row in enumerate(U.sort(rows, **ka)):
_continue = 0
for ic, ran in dcol_range.items():
# rt+=f'# {row}[{ic}]<hr>'
# _continue=0
if ic >= 0 and py.istr(row[ic]) and py.istr(ran):
if not ran in row[ic]:
_continue = 1
if ic < 0 and py.istr(row[ic]) and py.istr(ran):
if ran in row[ic]:
_continue = 1
if py.isnum(row[ic]) and py.isnum(ran[0]):
if not ran[0] <= row[ic] <= ran[1]:
_continue = 1
if _continue: continue
if 'item.taobao.com/item.htm?id=' in row[-3]:
row[-3] = T.sub(row[-3], 'id=', '')
tb = f'''{row[-1]}
<span>{row[:4]}</span> <br>
<a target="_blank" href="taobao://item.taobao.com/item.htm?id={row[-3]}">{'%4s'%index} {row[-2]} </a>
<br><hr>
'''
rt += tb
return rt
def request(url,
method='GET',
headers=gheaders,
proxies=AUTO_GET_PROXY,
verify=False,
no_raise=False,
print_req=False,
**ka):
'''
'''
import requests
U, T, N, F = py.importUTNF()
proxies, ka = auto_proxy(proxies, ka)
print_req = U.get_duplicated_kargs(ka,
'show',
'print',
'p',
'print_req',
default=print_req)
if (py.istr(url) and url.upper() in HTTP_METHODS):
# ka.pop('method','')#D.pop(k[,d]) -> v,
ka['method'] = url
url = ka['url'] # test url exists
elif method:
ka['method'] = method
if headers:
ka['headers'] = headers
for k in py.list(ka):
v = ka[k]
if py.istr(k) and py.istr(v):
if k[0].isupper():
ka.pop(k)
headers[k] = v
ka['verify'] = verify
if url and 'url' not in ka:
ka['url'] = url
ka['url'] = N.auto_url(ka['url'])
if print_req: print(U.v.requests.request(**ka))
if no_raise:
try:
return requests.request(**ka)
except Exception as e:
return py.No(e, ka)
return requests.request(**ka)
def setIndex(indexName):
'''#始终加载在此进程中第一次设置（或手动 sys.gsIndex=''）
'''
if not py.istr(indexName): raise py.ArgumentError('must str')
s = U.get('es_index')
if s:
globals()['gsIndex'] = s
def route(path="/", method=["GET"], h=True, args=True):
if not args: h = False
if py.istr(method):
method = method.upper()
if method in register_route:
method = [method]
else:
raise Exception('unsupported method:' + method)
def decorator(f):
for m in method:
m = m.upper()
try:
if h:
register_route[m][path] = f
else:
def wrap(handler, *a, **ka):
return f(*a, **ka)
register_route[m][path] = wrap #lambda handler:f()
except:
logging.error("{0} method is not available.".format(m))
return f
return decorator
def receive(request):
data = T.json_loads(request.get_data())
if not py.istr(data):
F.dill_dump(file=cache_path + 'dill/' + gid, obj=data)
return U.set_dict_value_list(did_err, gid, data)
if gid in did:
return U.set_dict_value_list(did2, gid, data)
did[gid] = F.write(cache_path + gid + '.html', data)
return gid
def get_one_article(pi):
if py.istr(pi) and '/p/' in pi:
pi=T.sub(pi,'/p/','')
if py.isint(pi):
pi=py.str(pi)
h=N.HTTP.getBytes("https://rss.lilydjwg.me/static_zhihu/"+pi)
h=h.decode("utf8")
t=T.html2text(h)
t=T.filterZh(t,11)
return t
async def chrome_devtools_protocol_send(url, astr, params={}, id=0):
astr = astr.strip()
if not id: id = U.ct()
if py.istr(astr) and not (astr.startswith('{') and astr.endswith('}')):
astr = py.dict(
id=id,
method=astr,
params=params,
)
if py.isdict(astr):
astr = T.json_dumps(astr)
return astr, await websocket_client_send(url, astr)
def replace_raw(raw_text, regex=True):
for i, v in gdraw.items():
if len(i) == 2 and isinstance(i, tuple):
if not regex: continue
if i[0] in raw_text:
raw_text = T.regexReplace(raw_text, i[1], str(v))
else:
if py.istr(i):
raw_text = raw_text.replace(str(i), str(v))
else:
U.log(['unknow gdraw', i, v])
return raw_text
def zhihu_question(id):
global c, next_url, answers, html, next_url
if py.istr(id):
id = T.filterInt(id, range(8, 11))[0]
start_url = 'https://www.zhihu.com/api/v4/questions/' + str(
id
) + '/answers?include=data%5B%2A%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Ccreated_time%2Cupdated_time%2Creview_info%2Crelevant_info%2Cquestion%2Cexcerpt%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%2A%5D.mark_infos%5B%2A%5D.url%3Bdata%5B%2A%5D.author.follower_count%2Cbadge%5B%2A%5D.topics&limit=5&offset=0&sort_by=default'
import requests
from bs4 import BeautifulSoup
import json
headers = {
'accept-language':
'zh-CN,zh;q=0.9',
'origin':
'https://www.zhihu.com',
'referer':
'https://www.zhihu.com/question/290268306',
'user-agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
}
next_url = [start_url]
answers = []
for url in next_url:
try:
html = requests.get(url, headers=headers, verify=False)
html.encoding = html.apparent_encoding
soup = BeautifulSoup(html.text, "lxml")
content = str(soup.p).split("<p>")[1].split("</p>")[0]
c = json.loads(content)
answers += pq(c)
next_url.append(c["paging"]["next"])
if c["paging"]["is_end"]:
break
except Exception as e:
globals()['err'] = e
continue
# for item in answers:
# print(item)
title = ''
try:
title = c['data'][0]['question']['title'] + f' | {len(answers)}'
except:
pass
U.log(title)
r = ''
for i, v in enumerate(answers):
r += f'\n[第{i+1}] {T.filterZh(v[0],11)} {v[1]}'
return title + r
def open_private_key(f, ):
'''
paramiko.RSAKey.from_private_key(open_private_key(f),) == <paramiko.rsakey.RSAKey at 0x23218fda648> '''
if py.isfile(f):
file = f
elif not py.istr(f):
raise py.ArgumentError('key f type must file or str', f)
elif F.exist(f):
file = py.open(f)
elif py.len(f) < 256 and 'PRIVATE KEY' not in f.upper():
raise py.ArgumentError(
'private_key f str format Error ! Or [%s] not exist' % f)
else:
from io import StringIO
file = StringIO(f)
return file
async def press_keys(page, *s, xy=(None, None)):
from qgb import Win
if len(s) == 1 and py.istr(s[0]):
key_defs = U.get(u_key_defs)
if not key_defs:
key_defs = []
for k, v in pyppeteer.us_keyboard_layout.keyDefinitions.items():
if py.len(k) > 1:
key_defs.append(k)
U.set(u_key_defs, key_defs)
## cache end
if s not in key_defs: # if in, s=tuple(skey)
s = s[0]
xy = Win.click(*xy)
for k in s:
await page.keyboard.press(k)
return s, xy
def taobao_sku(d):
'''item html :
Hub.config.set('sku', {
valCartInfo : {
itemId : '355190223
cartUrl: '//cart.ta
},
apiRelateMarket : '//t
apiAddCart : '//c
apiInsurance : '',
wholeSibUrl : '//d
areaLimit : '',
bigGroupUrl : '',
valPostFee : '',
coupon : {
couponApi :
couponWidgetDomain:
cbUrl :
},
valItemInfo : { #这里开始 大概 1424 行
defSelected: -1,
skuMap : {";162}
,propertyMemoMap: {...}
} # 这个 结束
'''
if py.istr(d): d = T.load_js_obj(d)
m = d['propertyMemoMap']
skuMap = d['skuMap']
r = []
for i, name in m.items():
row = []
pi = skuMap[';{};'.format(
i
)] # {'oversold': False, 'price': '1.80', 'skuId': '4451749127064', 'stock': '2'}
row = [
U.FloatRepr(pi['price'], size=8),
U.StrRepr(i, size=20),
U.StrRepr(name),
]
if pi['oversold']: row.append('oversold')
r.append(row)
return r
def search2xls(body,
index=gsIndex,
fields=('url', 'title', 'channel', 'column_classify',
'datetime'),
max_str_len=555):
''' Exception: String longer than 32767 characters '''
zh = T.filter_zh(py.repr(body))
es_data = es.search(index=index, body=body)['hits']['hits']
r = []
for i in es_data:
# if py.islist(i):
# U.log(i)
# continue
s = i['_source']
row = []
for c in fields:
c = s[c]
if py.istr(c): c = c[:max_str_len]
row.append(c)
r.append(row)
return F.write_xls('qgb-es-{}-{}.xls'.format(zh, py.len(r)), r)
def load(s,skip_err_load=0):
if py.istr(s):
ls=[i.strip() for i in s.split(',')]
if py.islist(s):
ls=s
print(ls)
r=[]
dlogin=U.get_or_set('lc.login',{})
for i in ls:
if not i:continue
f=r'C:/test/{}@qgbcs.uu.me.dill'.format(i)
q=F.dill_load(f)
if not q:
print('#Err',f,repr(q))
if skip_err_load:
continue
else:
raise q
dlogin[i]=q
r.append(q)
return r
async def get_page(page=None,
url=py.No(URL_TRADE_LIST),
wait=None,
browser=None):
global JS_ONLOAD
# py.pdb()()
if py.istr(page) and not url: # and ('://' in page)
url, page = page, None
if not browser: browser = await get_browser()
if not page and not url:
return (await browser.pages())[-1]
if not url: url = URL_TRADE_LIST
if not wait and not page:
page = await _get_page_by_url(browser, url)
if wait and not page:
start = U.timestamp()
while not page:
page = await _get_page_by_url(browser, url)
await A.sleep(py.max(0.1, wait / 10))
if U.timestamp() - start > wait:
return py.No('%s sec timeout!,can not found page.url:%s' %
(wait, url))
return U.set('page', page)
def filter_args(args_dict):
'''
pymysql.connect(**ka={
host(str): MySQL服务器地址
port(int): MySQL服务器端口号
user(str): 用户名
passwd(str): 密码
db(str): 数据库名称
charset(str): 连接编码
}
'''
r={}
for k,v in args_dict.items():
if not py.istr(k):continue
k=k.lower()
if k=='port':
v=py.int(v) # importU().
if k=='PASSWORD'.lower():k='passwd'
if k=='NAME'.lower() :k='db'
if k in gargs_list:
r[k]=v
return r
