def zippy_share(url: str) -> str:
""" ZippyShare direct links generator
Based on https://github.com/KenHV/Mirror-Bot """
link = re.findall("https:/.(.*?).zippyshare", url)[0]
response_content = (requests.get(url)).content
bs_obj = BeautifulSoup(response_content, "lxml")
try:
js_script = bs_obj.find("div", {
"class": "center",
}).find_all("script")[1]
except:
js_script = bs_obj.find("div", {
"class": "right",
}).find_all("script")[0]
js_content = re.findall(r'\.href.=."/(.*?)";', str(js_script))
js_content = 'var x = "/' + js_content[0] + '"'
evaljs = EvalJs()
setattr(evaljs, "x", None)
evaljs.execute(js_content)
js_content = getattr(evaljs, "x")
return f"https://{link}.zippyshare.com{js_content}"
def zippy_share(url: str) -> str:
""" ZippyShare direct links generator
Based on https://github.com/KenHV/Mirror-Bot
https://github.com/jovanzers/WinTenCermin """
try:
link = re.findall(r'\bhttps?://.*zippyshare\.com\S+', url)[0]
except IndexError:
raise DirectDownloadLinkException("No Zippyshare links found")
try:
base_url = re.search('http.+.zippyshare.com', link).group()
response = requests.get(link).content
pages = BeautifulSoup(response, "lxml")
try:
js_script = pages.find("div", {"class": "center"}).find_all("script")[1]
except IndexError:
js_script = pages.find("div", {"class": "right"}).find_all("script")[0]
js_content = re.findall(r'\.href.=."/(.*?)";', str(js_script))
js_content = 'var x = "/' + js_content[0] + '"'
evaljs = EvalJs()
setattr(evaljs, "x", None)
evaljs.execute(js_content)
js_content = getattr(evaljs, "x")
return base_url + js_content
except IndexError:
raise DirectDownloadLinkException("ERROR: Can't find download button")
def deciphered_signature(self, signature=None, algo_js=None):
#Returns the final deciphered signature by executing the Javascript
algo_js = algo_js.replace(
re.search(r'var output.*?"(.*?)"', algo_js).groups()[0], signature)
context = EvalJs()
context.execute(algo_js)
return context.output
async def zippy_share(url: str) -> str:
link = re.findall("https:/.(.*?).zippyshare", url)[0]
response_content = (requests.get(url)).content
bs_obj = BeautifulSoup(response_content, "lxml")
try:
js_script = bs_obj.find("div", {
"class": "center",
}).find_all("script")[1]
except BaseException:
js_script = bs_obj.find("div", {
"class": "right",
}).find_all("script")[0]
js_content = re.findall(r'\.href.=."/(.*?)";', str(js_script))
js_content = 'var x = "/' + js_content[0] + '"'
evaljs = EvalJs()
setattr(evaljs, "x", None)
evaljs.execute(js_content)
js_content = getattr(evaljs, "x")
dl_url = f"https://{link}.zippyshare.com{js_content}"
file_name = basename(dl_url)
return f"[{urllib.parse.unquote_plus(file_name)}]({dl_url})"
def getTk(self):
with open('.\\config\\GoogleJS.js', encoding='utf8') as f:
js_data = f.read()
context = EvalJs()
context.execute(js_data)
tk = context.TL(self.text)
return tk
def getTk(self, text):
with open(this_file_dir + '/GoogleJS.js', encoding='utf8') as f:
js_data = f.read()
context = EvalJs()
context.execute(js_data)
tk = context.TL(text)
return tk
def create_js_context(self):
with self._context_lock:
if self._context is None:
registered_context = self._registered_context
registered_context[self.MVAR_VARS] = {}
self._context = EvalJs(context=registered_context,
enable_require=True)
if self._prepare_script:
for script in self._prepare_script:
self._context.execute(script)
def get_episode_links(self, item):
url = f"https://manhua.dmzj.com/{item['path']}#@page=1"
res = r.get(url)
# 信息被JS加密，需要用内置的JS编译
soup = bs4.BeautifulSoup(res.text, features="lxml")
head_script = soup.head.script.string
js = EvalJs()
js.execute(head_script)
# 从编译JS的结果提取信息
item["links"] = [HOST + i for i in json.loads(js.pages)]
item["sname"] = f"{js.g_comic_name}"
item["chapter"] = f"{js.g_chapter_name}"
def decrypt(data):
if six.PY2:
with open(os.path.join(os.path.dirname(__file__),
"primewire.js")) as f:
code = f.read()
jscntx = EvalJs()
jscntx.execute(code)
return jscntx.decode(data)
else:
from bfish import Cipher
from textwrap import wrap
e = data[:9].encode()
t = data[9:]
bd = base64.b64decode(t)
bf = Cipher(bytearray(e))
out = b""
for chunk in bf.decrypt_ecb(bd):
out += chunk
return wrap(out.decode(), 5)
import sys
import tqdm
from multiprocessing import Pool
from collections import defaultdict
#gbids_to_coord = defaultdict(list)
fasta_file = "/mnt/gnpn/gnpn/projects/orphanpks/TargetMining/Blast/blast_results_seqs/blast_results.KS.fasta.cleanName.cdhit.99"
# Head of cdhit file:
# >AVFP01000283.1__724_1992_Microbial_mat_metagenome_scaffold_282__whole_genome_shotgun_sequence_0_1_9914_7e-169
# IAIIGMSGIFPDAEDVQTYWNNLCQGR
# >AM746676___5843905_5845200__0_-1_13033779_0.0
count = 0
context = EvalJs()
# Output file with number of gbids on which antismash was run
outfilefaa = "sequences.faa.21k.coord.fasta"
ff = open(outfilefaa, "w")
antismash_dir = "antismash_output_assemblies_all/"
for gbidfull in tqdm.tqdm(os.listdir(antismash_dir)):
#if not gbidfull.startswith("CP012600"):
# continue
#print gbidfull
if len(gbidfull.split("_")) > 2:
gbid = gbidfull.rsplit("_", 2)[0]
blast_coord_start, blast_coord_end = gbidfull.split("_")[1:]
#print "here", gbid, blast_coord_start, blast_coord_end
#!/usr/bin/env python
import json
import io
from js2py import EvalJs
js_file = io.open('lib/index.js', 'r', encoding="utf-8")
js_code = js_file.read()
context = EvalJs()
context.execute(js_code)
create_doc_json = context.prosemirror.create_doc_json
transform_doc_json = context.prosemirror.transform_doc_json
spec_data_json = '{"nodes":{"content":["doc",{"content":"article","selectable":false},"article",{"defining":true,"content":"title subtitle authors abstract keywords body","selectable":false,"allowGapCursor":false,"attrs":{"papersize":{"default":"A4"},"citationstyle":{"default":""},"documentstyle":{"default":""},"language":{"default":"en-US"},"tracked":{"default":false}},"parseDOM":[{"tag":"div.article"}]},"title",{"content":"text*","marks":"annotation track","group":"part","defining":true,"parseDOM":[{"tag":"div.article-title"}]},"subtitle",{"content":"text*","marks":"annotation track","group":"part","defining":true,"attrs":{"hidden":{"default":true}},"parseDOM":[{"tag":"div.article-subtitle"}]},"authors",{"content":"author*","marks":"annotation track","group":"part","defining":true,"attrs":{"hidden":{"default":true}},"parseDOM":[{"tag":"div.article-authors"}]},"author",{"inline":true,"draggable":true,"attrs":{"firstname":{"default":false},"lastname":{"default":false},"email":{"default":false},"institution":{"default":false}},"parseDOM":[{"tag":"span.author"}]},"abstract",{"content":"(block | table_block)+","group":"part","marks":"annotation","defining":true,"attrs":{"hidden":{"default":true}},"parseDOM":[{"tag":"div.article-abstract"}]},"keywords",{"content":"keyword*","marks":"annotation track","group":"part","defining":true,"attrs":{"hidden":{"default":true}},"parseDOM":[{"tag":"div.article-keywords"}]},"keyword",{"inline":true,"draggable":true,"attrs":{"keyword":{"default":""}},"parseDOM":[{"tag":"span.keyword"}]},"body",{"content":"(block | table_block)+","group":"part","marks":"annotation track","defining":true,"parseDOM":[{"tag":"div.article-body"}]},"paragraph",{"group":"block","content":"inline*","attrs":{"track":{"default":[]}},"parseDOM":[{"tag":"p"}]},"blockquote",{"content":"block+","group":"block","attrs":{"track":{"default":[]}},"marks":"annotation","defining":true,"parseDOM":[{"tag":"blockquote"}]},"horizontal_rule",{"group":"block","attrs":{"track":{"default":[]}},"parseDOM":[{"tag":"hr"}]},"figure",{"group":"block","attrs":{"equation":{"default":""},"image":{"default":false},"figureCategory":{"default":""},"caption":{"default":""},"id":{"default":false},"track":{"default":[]}},"parseDOM":[{"tag":"figure"}]},"heading",{"group":"block","content":"inline*","marks":"_","defining":true,"attrs":{"level":{"default":1},"id":{"default":false},"track":{"default":[]}},"parseDOM":[{"tag":"h1"},{"tag":"h2"},{"tag":"h3"},{"tag":"h4"},{"tag":"h5"},{"tag":"h6"}]},"code_block",{"content":"text*","marks":"annotation track","group":"block","code":true,"defining":true,"attrs":{"track":{"default":[]}},"parseDOM":[{"tag":"pre","preserveWhitespace":"full"}]},"text",{"group":"inline"},"hard_break",{"inline":true,"group":"inline","selectable":false,"parseDOM":[{"tag":"br"}]},"citation",{"inline":true,"group":"inline","attrs":{"format":{"default":"autocite"},"references":{"default":[]}},"parseDOM":[{"tag":"span.citation"}]},"equation",{"inline":true,"group":"inline","attrs":{"equation":{"default":""}},"parseDOM":[{"tag":"span.equation"}]},"footnote",{"inline":true,"group":"inline","attrs":{"footnote":{"default":[{"type":"paragraph"}]}},"parseDOM":[{"tag":"span.footnote-marker[data-footnote]"}]},"ordered_list",{"group":"block","content":"list_item+","attrs":{"order":{"default":1},"track":{"default":[]}},"parseDOM":[{"tag":"ol"}]},"bullet_list",{"group":"block","content":"list_item+","attrs":{"track":{"default":[]}},"parseDOM":[{"tag":"ul"}]},"list_item",{"content":"block+","marks":"annotation","attrs":{"track":{"default":[]}},"parseDOM":[{"tag":"li"}],"defining":true},"table",{"content":"table_row+","tableRole":"table","isolating":true,"group":"table_block","parseDOM":[{"tag":"table"}],"attrs":{"track":{"default":[]}}},"table_row",{"content":"(table_cell | table_header)*","tableRole":"row","parseDOM":[{"tag":"tr"}]},"table_cell",{"marks":"annotation","content":"block+","attrs":{"colspan":{"default":1},"rowspan":{"default":1},"colwidth":{"default":null}},"tableRole":"cell","isolating":true,"parseDOM":[{"tag":"td"}]},"table_header",{"content":"block+","attrs":{"colspan":{"default":1},"rowspan":{"default":1},"colwidth":{"default":null}},"tableRole":"header_cell","isolating":true,"parseDOM":[{"tag":"th"}]}]},"marks":{"content":["em",{"parseDOM":[{"tag":"i"},{"tag":"em"},{"style":"font-style=italic"}]},"strong",{"parseDOM":[{"tag":"strong"},{"tag":"b"},{"style":"font-weight"}]},"link",{"attrs":{"href":{},"title":{"default":null}},"inclusive":false,"parseDOM":[{"tag":"a[href]"}]},"code",{"parseDOM":[{"tag":"code"}]},"comment",{"attrs":{"id":{}},"inclusive":false,"excludes":"","group":"annotation","parseDOM":[{"tag":"span.comment[data-id]"}]},"annotation_tag",{"attrs":{"type":{"default":""},"key":{"default":""},"value":{"default":""}},"inclusive":false,"excludes":"","group":"annotation","parseDOM":[{"tag":"span.annotation-tag[data-type]"}]},"anchor",{"attrs":{"id":{"default":false}},"inclusive":false,"group":"annotation","parseDOM":[{"tag":"span.anchor[data-id]"}]},"deletion",{"attrs":{"user":{"default":0},"username":{"default":""},"date":{"default":0}},"inclusive":false,"group":"track","parseDOM":[{"tag":"span.deletion"}]},"insertion",{"attrs":{"user":{"default":0},"username":{"default":""},"date":{"default":0},"approved":{"default":true}},"inclusive":false,"group":"track","parseDOM":[{"tag":"span.insertion"},{"tag":"span.approved-insertion"}]},"format_change",{"attrs":{"user":{"default":0},"username":{"default":""},"date":{"default":0},"before":{"default":[]},"after":{"default":[]}},"inclusive":false,"group":"track","parseDOM":[{"tag":"span.format-change"}]}]}}'
doc_data_json = '{"type":"doc","content":[{"type":"article","attrs":{"papersize":"A4","citationstyle":"apa","documentstyle":"elephant","language":"en-US","tracked":false},"content":[{"type":"title","content":[{"type":"text","marks":[{"type":"insertion","attrs":{"user":1,"username":"******","date":25710790,"approved":true}}],"text":"testing"}]},{"type":"subtitle","attrs":{"hidden":true}},{"type":"authors","attrs":{"hidden":true}},{"type":"abstract","attrs":{"hidden":true},"content":[{"type":"paragraph","attrs":{"track":[]}}]},{"type":"keywords","attrs":{"hidden":true}},{"type":"body","content":[{"type":"paragraph","attrs":{"track":[]},"content":[{"type":"text","marks":[{"type":"insertion","attrs":{"user":1,"username":"******","date":25710790,"approved":true}}],"text":"the body"}]}]}]}]}'
doc = create_doc_json(doc_data_json, spec_data_json)
step_data_json = '[{"stepType":"replace","from":27,"to":27,"slice":{"content":[{"type":"text","marks":[{"type":"insertion","attrs":{"user":1,"username":"******","date":25710790,"approved":true}}],"text":"X"}]}},{"stepType":"addMark","mark":{"type":"insertion","attrs":{"user":1,"username":"******","date":25716230,"approved":true}},"from":27,"to":28}]'
import time
a = range(100)
start = time.time()
for i in a:
new_doc = transform_doc_json(step_data_json, doc)
new_doc.toJSON()
stop = time.time()
print((stop - start) / 100)
class PyJsEngineBase:
DEFAULT_ENCODING = 'utf-8'
common_bufsize = 1024
JS_EXT_NAME = ".js"
EXT_NAME_SET = {'', JS_EXT_NAME}
MVAR_PREFIX = "__"
MVAR_VARS = "__vars__"
MVAR_SCRIPT_NAME = "__script_name__"
MVAR_WORKING_DIR = "__working_dir__"
def __init__(self, logger=None, **kwargs):
self._logger = logger or get_logger()
self._script = None
self._registered_context = {}
self._prepare_script = []
self._path = list()
self._context = None
self._context_lock = Lock()
self.MVAR_SET = {
self.MVAR_SCRIPT_NAME,
self.MVAR_WORKING_DIR,
}
@property
def path(self):
return self._path
def add_to_path(self, path):
if isinstance(path, str):
self._path.insert(0, path)
@property
def script(self):
return self._script
@property
def context(self):
with self._context_lock:
return self._context
def do_before(self, jskwargs, *args):
pass
def do_after(self, jskwargs, *args):
pass
def wrapped_method(self, jskwargs, *args, func=None):
self.do_before(jskwargs, *args)
result = None
if func is not None:
result = func(jskwargs, *args)
self.do_after(jskwargs, *args)
return result
# 注册上下文（context）
def register_context(self, context):
if isinstance(context, dict):
new_context = copy(context)
for k, v in context.items():
if isinstance(v, types.MethodType) and getattr(
self, v.__name__):
new_context[k] = partial(self.wrapped_method, func=v)
self._registered_context.update(new_context)
# 强制将非MVAR_PREFIX开头的键名改为大写字母开头
for k in list(self._registered_context.keys()):
if isinstance(k, str) and not k.startswith(self.MVAR_PREFIX):
if k != k.capitalize():
v = self._registered_context.pop(k)
new_k = k.capitalize()
self._registered_context[new_k] = v
# 清除预备脚本列表
def clear_prepare_script(self):
self._prepare_script.clear()
# 往预备脚本列表添加要预执行的脚本
def append_prepare_script(self, script):
self._prepare_script.append(script)
# 创建JS上下文对象
def create_js_context(self):
with self._context_lock:
if self._context is None:
registered_context = self._registered_context
registered_context[self.MVAR_VARS] = {}
self._context = EvalJs(context=registered_context,
enable_require=True)
if self._prepare_script:
for script in self._prepare_script:
self._context.execute(script)
# 加载脚本
def load(self, script):
if isinstance(script, str):
self._script = script
else:
raise ValueError("Script must be type 'str'!")
# 加载脚本（从文件）
def load_from_file(self, file, encoding=None):
script = self.read_from_file(file, encoding=encoding)
# 切换到脚本文件所在路径
try:
base_name = os.path.basename(file)
dirname = os.path.abspath(file)
dirname = os.path.dirname(dirname)
# os.chdir(dirname)
# logger.debug(msg='OS change to script''s directory (%s)' % (dirname))
var_dict = self._registered_context
var_dict[self.MVAR_SCRIPT_NAME] = os.path.splitext(base_name)[0]
var_dict[self.MVAR_WORKING_DIR] = dirname
self._path.clear()
self.add_to_path(os.path.abspath('.')) # 最后：程序目录
self.add_to_path(dirname) # 倒数第二：脚本目录
except:
pass
self.load(script)
# 加载脚本（从字串）
def load_from_string(self, source):
script = self.read_from_string(source)
self.load(script)
# 读取脚本文件
def read_from_file(self, file, encoding=None):
logger = self._logger
logger.debug(msg="Loading script from file...")
fp = None
try:
if isinstance(file, str):
c = encoding
if c is None:
# 如无自定义文件编码，先读文件自动检测编码
tmpf = open(file=file, mode='rb')
tmps = tmpf.read(self.common_bufsize)
tmpchd = crd.detect(tmps)
logger.debug(msg="Encoding detected: %s" % (repr(tmpchd)))
# 再用codecs按检测到的编码读取内容
c = tmpchd['encoding']
fp = cdc.open(file, encoding=c)
else:
fp = file
script = self.read_from_string(fp.read())
return script
finally:
if fp is not None and isinstance(file, str):
fp.close()
# 读取脚本数据
def read_from_string(self, source):
if isinstance(source, str):
return source
elif isinstance(source, bytes):
return source.decode(self.DEFAULT_ENCODING)
return None
# 执行脚本
def run(self, temp_script=None):
script = temp_script
if script is None:
script = self._script
self.create_js_context()
self.context.execute(script)
def get_vars(self):
return self.context[self.MVAR_VARS]
def get_vars_dict(self, vars=None):
if vars is None:
# 如未指定vars，则使用内置上下文vars
vars = self.get_vars()
if isinstance(vars, JsObjectWrapper):
# 确保vars为非JsObjectWrapper
vars = vars.to_dict()
return vars
# 解析参数字典（所有参数；仅做类型转换）
@staticmethod
def args_parser_all(jskwargs):
return jskwargs.to_dict() if isinstance(jskwargs,
JsObjectWrapper) else jskwargs
# 解析参数字典，按规则规范参数格式及赋予默认值
# jskwargs Js传递的参数字典，rules 解析规则字典（格式：{key:(name, type, default)}，type有 s字串/sr原始字串/i整数/r实数/b布尔 ）
def args_parser(self, jskwargs, rules):
if not isinstance(rules, dict):
return None
if isinstance(jskwargs, JsObjectWrapper):
# 确保jskwargs为非JsObjectWrapper
jskwargs = jskwargs.to_dict()
if not isinstance(jskwargs, dict):
return None
args = {}
keys = set(jskwargs.keys())
for pk, pv in rules.items():
if isinstance(pk, str) and isinstance(pv,
tuple) and len(pv) in {2, 3}:
# pk: key, pn: name, pt: type, pd: default
lpv = len(pv)
if lpv == 2:
pn, pt = pv
pd = None
if pk not in keys:
continue
else:
pn, pt, pd = pv
value = jskwargs.get(pk, pd)
if isinstance(value, bytes):
value = value.decode(self.DEFAULT_ENCODING)
if pt in {'s', 'i', 'r', 'b'}:
value = self.var_replacer(value) if isinstance(
value, str) else value
if pt in {'s', 'sr'}:
args[pn] = str(value) if value is not None else None
elif pt in {'i', 'ir'}:
args[pn] = (int(eval(str(value))) if value is not None else
None) if not isinstance(value, int) else value
elif pt in {'r', 'rr'}:
args[pn] = (eval(str(value)) if value is not None else None
) if not isinstance(value, float) else value
elif pt in {'b', 'br'}:
args[pn] = str(value).lower() == str(True).lower()
if self.MVAR_VARS not in args:
try:
args[self.MVAR_VARS] = self.get_vars_dict()
except:
pass
return args
# 变量标识替换
def var_replacer(self,
v_str,
vars=None,
v_prefix=r"$%",
v_suffix=r"%$",
re_prefix=r"\$\%",
re_suffix=r"\%\$"):
vars = self.get_vars_dict(vars=vars)
return self.var_replacer_raw(vars,
v_str,
v_prefix=v_prefix,
v_suffix=v_suffix,
re_prefix=re_prefix,
re_suffix=re_suffix)
# 变量标识替换（原始方法）
@staticmethod
def var_replacer_raw(var_dict,
v_str,
v_prefix=r"$%",
v_suffix=r"%$",
re_prefix=r"\$\%",
re_suffix=r"\%\$"):
keys = re.findall(re_prefix + r"(.+?)" + re_suffix, v_str)
d_keys = []
for i in keys:
value = var_dict.get(i)
if value is not None:
d_keys.append(i)
o_str = deepcopy(v_str)
for i in d_keys:
# 注：这里var_dict.get(i)需要强制转字符串，适应var_dict中保存包含字符串以外类型对象的情况
o_str = o_str.replace(v_prefix + i + v_suffix,
str(var_dict.get(i)))
return o_str
def get_orfs(gbidfull, antismash_dir, gene_outfile, ks_outfile, stdoutfile):
filename = os.path.join(antismash_dir, gbidfull, "geneclusters.js")
if not os.path.exists(filename):
print "Not found %s" % filename
return
gbid, gbid_start, gbid_end = parse_gbidfull(gbidfull)
# Read antismash json file
f = open(filename, 'r')
data_js = f.read()
context = EvalJs()
context.execute(data_js)
geneclusters = context.geneclusters.to_dict()
details_data = context.details_data.to_dict()
for cluster_id in geneclusters.iterkeys():
# Parse only pks clusters:
clustertype = geneclusters[cluster_id]["type"]
pkss = ['t1pks', 'transatpks']
if not any(pks in clustertype for pks in pkss):
continue
# Correct gene coord if gbid sequence was split
antismash_start = int(geneclusters[cluster_id]["start"])
antismash_end = int(geneclusters[cluster_id]["end"])
cluster_start = gbid_start + antismash_start
cluster_end = gbid_start + antismash_end
print "Cluster ", cluster_id, cluster_start, cluster_end, "....."
locus_coords = {}
for orfs in geneclusters[cluster_id]["orfs"]:
antismash_prot_start = int(orfs["start"])
antismash_prot_end = int(orfs["end"])
#print antismash_prot_start, antismash_prot_end
# Correct gene coord if gbid sequence was split
prot_start = gbid_start + antismash_prot_start
prot_end = gbid_start + antismash_prot_end
locus_tag = orfs["locus_tag"]
locus_coords[locus_tag] = (prot_start, prot_end)
description = orfs["description"]
name1 = description.split("</span><br>")[0]
name = name1.split("<span class=\"svgene-tooltip-bold\">")[1]
d = description.split("QUERY=")[1]
sequence1 = d.split("_LOC=protein")[0]
sequence = sequence1.split("&LINK")[0]
# Write protein sequences in a fasta file
fasta_id = ">%s|%s|%s-%s|%s|%s-%s|%s" % \
(gbid, cluster_id, cluster_start, cluster_end,
clustertype, prot_start, prot_end, locus_tag)
gene_outfile.write("%s\n%s\n" % (fasta_id, sequence))
if not details_data:
print "%s\t%s\tEmpty details_data" % \
(gbidfull, abs(cluster_end - cluster_start))
stdoutfile.write("%s\t%s\tEmpty details_data\n" %
(gbidfull, abs(cluster_end - cluster_start)))
continue
for orfs in details_data[cluster_id]["orfs"]:
locus_tag = orfs["id"]
for domain in orfs["domains"]:
domain_type = domain["type"]
if domain_type != "PKS_KS":
continue
ks_seq = domain["sequence"]
ks_start = locus_coords[locus_tag][0] + int(domain["start"])
ks_end = locus_coords[locus_tag][0] + int(domain["end"])
print "KS %s %s %s" % (ks_start, ks_end, ks_seq[:20])
# Write protein sequences in a fasta file
fasta_id = ">%s|%s|%s-%s|%s|%s-%s|%s|%s" % \
(gbid, cluster_id, cluster_start, cluster_end,
clustertype, ks_start, ks_end, locus_tag, domain_type)
ks_outfile.write("%s\n%s\n" % (fasta_id, ks_seq))
def _download(client, message):
user_id = message.from_user.id
if not message.media:
sent_message = message.reply_text('🕵️**Checking link...**', quote=True)
if message.command:
link = message.command[1]
else:
link = message.text
if 'drive.google.com' in link:
sent_message.edit(Messages.CLONING.format(link))
LOGGER.info(f'Copy:{user_id}: {link}')
msg = GoogleDrive(user_id).clone(link)
sent_message.edit(msg)
elif 'mediafire.com' in link:
""" MediaFire """
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
try:
link = re.findall(r'\bhttps?://.*mediafire\.com\S+', url)[0]
except IndexError:
return sent_message.edit(
"No MediaFire links found\nMight Be File/Files Deleted. \nOpen The Link And Check"
)
page = BeautifulSoup(requests.get(link).content, 'lxml')
info = page.find('a', {'aria-label': 'Download file'})
link = info.get('href')
sent_message.edit(Messages.DOWNLOADING.format(link))
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
# LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
else:
sent_message.edit(
Messages.DOWNLOAD_ERROR.format(file_path, link))
elif 'zippyshare.com' in link:
""" ZippyShare """
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
try:
link = re.findall(r'\bhttps?://.*zippyshare\.com\S+', url)[0]
except IndexError:
raise DirectDownloadLinkException("No Zippyshare links found")
try:
base_url = re.search('http.+.zippyshare.com', link).group()
response = requests.get(link).content
pages = BeautifulSoup(response, "lxml")
try:
js_script = pages.find("div", {
"class": "center"
}).find_all("script")[1]
except IndexError:
js_script = pages.find("div", {
"class": "right"
}).find_all("script")[0]
js_content = re.findall(r'\.href.=."/(.*?)";', str(js_script))
js_content = 'var x = "/' + js_content[0] + '"'
evaljs = EvalJs()
setattr(evaljs, "x", None)
evaljs.execute(js_content)
js_content = getattr(evaljs, "x")
link = base_url + js_content
except IndexError:
raise sent_message.edit("ERROR: Can't find download button")
sent_message.edit(Messages.DOWNLOADING.format(link))
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
# LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
else:
sent_message.edit(
Messages.DOWNLOAD_ERROR.format(file_path, link))
elif 'anonfiles.com' in link:
""" Anonfiles """
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
bypasser = lk21.Bypass()
link = bypasser.bypass_anonfiles(link)
sent_message.edit(Messages.DOWNLOADING.format(link))
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
# LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
else:
sent_message.edit(
Messages.DOWNLOAD_ERROR.format(file_path, link))
elif 'bayfiles.com' in link:
""" Bayfiles """
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
bypasser = lk21.Bypass()
link = bypasser.bypass_anonfiles(link)
sent_message.edit(Messages.DOWNLOADING.format(link))
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
# LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
elif 'racaty.net' in link:
""" Racaty """
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
dl_url = ''
try:
link = re.findall(r'\bhttps?://.*racaty\.net\S+', url)[0]
except IndexError:
raise ("No Racaty links found\n")
scraper = cfscrape.create_scraper()
r = scraper.get(url)
soup = BeautifulSoup(r.text, "lxml")
op = soup.find("input", {"name": "op"})["value"]
ids = soup.find("input", {"name": "id"})["value"]
rpost = scraper.post(url, data={"op": op, "id": ids})
rsoup = BeautifulSoup(rpost.text, "lxml")
dl_url = rsoup.find("a",
{"id": "uniqueExpirylink"})["href"].replace(
" ", "%20")
link = dl_url
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
else:
sent_message.edit(
Messages.DOWNLOAD_ERROR.format(file_path, link))
# elif '1fichier.com' in link:
elif 'ouo.press' in link or 'ouo.io' in link:
""" Ouo Bypass """
bypasser = lk21.Bypass()
link = bypasser.bypass_ouo(link)
sent_message.edit(
f"Bypassed The Ouo Link That U Provided.\n\nLink = `{link}`")
# elif is_gdtot_link(link):
else:
if '|' in link:
link, filename = link.split('|')
link = link.strip()
filename.strip()
dl_path = os.path.join(
f'{Config.DOWNLOAD_DIRECTORY}/{filename}')
else:
link = link.strip()
filename = os.path.basename(link)
dl_path = Config.DOWNLOAD_DIRECTORY
LOGGER.info(f'Download:{user_id}: {link}')
sent_message.edit(Messages.DOWNLOADING.format(link))
result, file_path = download_file(link, dl_path)
if result == True:
sent_message.edit(
Messages.DOWNLOADED_SUCCESSFULLY.format(
os.path.basename(file_path),
humanbytes(os.path.getsize(file_path))))
msg = GoogleDrive(user_id).upload_file(file_path)
sent_message.edit(msg)
LOGGER.info(f'Deleteing: {file_path}')
os.remove(file_path)
else:
sent_message.edit(
Messages.DOWNLOAD_ERROR.format(file_path, link))