def __get_url_curl(self, post, referer):
"""
:param post:
:param referer:
:return:
"""
headers = {
"user-agent": getUserAgent(),
"origin": "https://www.pelisplay.tv",
"referer": referer
}
url = "https://www.pelisplay.tv/entradas/procesar_player"
data = curlData(url, value=post, cookie=self.cookie, header=headers)
try:
data = json.loads(data)
except Exception as e:
lock.acquire()
self.get_cookie()
lock.release()
if self.cookie_get_num < 3:
return self.__get_url_curl(post, referer=referer)
else:
data = {"estado": 500}
debug("播放链接获取出错，错误信息：{error}".format(error=e))
if data['estado'] == 200:
data = data['data']
else:
data = ""
self.cookie_get_num = 0
return data
def get_cookie(self):
header = {
"User-Agent": getUserAgent(),
# "Cache-Control": "max-age=0",
# "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3"
}
url = "https://www.pelisplay.tv/"
self.cookie = getCookie(url, header=header)
debug(self.cookie)
def __init__(self):
# 数据库连接全局变量
self.ws_db = phoenix_db.DBConfig()
self.config = config
# 全局代理IP
self.proxy_ip = ""
self.is_change_proxy = 0
self.guid = ""
self.cookie = ""
self.ip_over = 0
self.user_agent_index = int((random.random()) * 1000) % getUserAgent(2)
self.table_columns = self.ws_db.getColumns({"table": "ws_docid"})
def __handle_data(self, item):
url = "https://www.pelisplay.tv" + item['img_src']
header = {
# "Referer": "https://www.pelisplay.tv/",
"User-Agent": getUserAgent(),
"Accept": "image/webp,image/apng,image/*,*/*;q=0.8"
}
data = curlData(url, header=header)
with open("static/images/{id}.jpg".format(id=item['id']), "wb") as f:
try:
data = data.encode("utf-8")
except Exception as e:
debug(e)
f.write(data)
self.__update_data(item)
f.close()
return {"code": 0}
def get_image():
url = request.values.get("url")
if url is not None:
domain = "https://www.pelisplay.tv"
url = urllib.parse.unquote(url)
final_url = domain + url
header = {
"Referer": "https://www.pelisplay.tv/",
"User-Agent": getUserAgent(),
"Accept": "image/webp,image/apng,image/*,*/*;q=0.8"
}
data = curlData(final_url, header=header, open_virtual_ip=True)
ext = re.findall("[\w\W]*?\.([\w\W]*.)", url)[0]
else:
ext = "jpg"
data = ""
# debug(data)
return Response(data, mimetype=get_image_type(ext))
def getCookie(self, url):
if self.ip_over == 1:
return 0
header = {
"User-Agent": getUserAgent(index=self.user_agent_index)
}
try:
cookie = getCookie(url, referer="http://wenshu.court.gov.cn", header=header, proxy_ip=self.proxy_ip,
timeout=5)
return cookie
except Exception as e:
if self.is_change_proxy > 4:
self.setProxyIp()
self.is_change_proxy = 0
else:
self.is_change_proxy = self.is_change_proxy + 1
if e.__str__().find("HTTPConnectionPool") != -1:
debug("cookie获取出错，HttpConnect错误，重新获取ip并重新获取")
return self.getCookie(url)
else:
return 0
def __get_video_src(self, item):
header = {
# "Referer": "http://www.wyysdsa.com/",
"User-Agent": getUserAgent(),
# "Cache-Control": "max-age=0",
# "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3"
}
# url = "http://zeus.pelisplay.tv/embed/vip.php?u=Q1A5NUZJM1VDTWlUTk8wTEFmWGNQZDhnbWRIcmt6UVU0VGIxakpXOUF4Mi9yZW51Zi9yaXZlcXFoYnlwL3picC5hYm1uem4uampqLy86ZmNnZ3U&fondo_requerido="
# url = "https://nl.tan90.club/test/testHeader.html"
data = curlData(url=item['url'], header=header, cookie=self.cookie)
# with open("tmp/content_detail.txt", "rb") as f:
# data = f.read().decode("utf-8")
# f.close()
try:
src = re.findall("JSON\.parse\('([\w\W]*?)'\)\);", data)[0]
src = src.replace("\\", "")
src = json.loads(src)
src = src[0]['file']
except Exception as e:
src = ""
debug(e)
return src
def getUrlAndCookieCaseType(self, court_name, start_date, end_date, case_type):
"""
拼装url同时得到cookie
:param court_name:
:param start_date:
:param end_date:
:param case_type
:return: param 包含线程所需所有参数 (dict)
"""
# 获取guid
header_1 = {
"User-Agent": getUserAgent(index=self.user_agent_index),
"Origin": "http://wenshu.court.gov.cn"
}
try:
num_flag = 0
guid = curlData("http://ws_api.xiezhi.sc.cn/getParam?vjkl5=0")
guid = json.loads(guid)
guid = guid['guid']
number = ""
# try:
# number = curlData("http://wenshu.court.gov.cn/ValiCode/GetCode", {"guid": guid}, header=header_1,
# referer="http://wenshu.court.gov.cn",
# proxy_ip=self.proxy_ip, timeout=5)
# except:
# number = "remind"
# while number.find("remind") != -1 or number.find("html") != -1 or number.find("服务不可用") != -1:
# if num_flag > 4:
# self.setProxyIp()
# num_flag = 0
# else:
# num_flag = num_flag + 1
# debug("number获取出错，继续获取")
# try:
# number = curlData("http://wenshu.court.gov.cn/ValiCode/GetCode", {"guid": guid}, header=header_1,
# referer="http://wenshu.court.gov.cn",
# proxy_ip=self.proxy_ip, timeout=5)
# except Exception as e:
# debug(e)
# sleep(0.5)
except:
debug("guid获取出错")
return self.getUrlAndCookieCaseType(court_name, start_date, end_date, case_type)
# 拼装url
url = "http://wenshu.court.gov.cn/list/list/?sorttype=1&number=%s&guid=%s&conditions=searchWord+%s+SLFY++%s&conditions=searchWord++CPRQ++%s%%20TO%%20%s&conditions=searchWord+%s+AJLX++%s" % (
number, guid, urllib.parse.quote(str(court_name)), urllib.parse.quote("法院名称:%s" % court_name),
urllib.parse.quote(str(start_date)), urllib.parse.quote(str(end_date)),
str(self.getCaseTypeIndex(case_type)), urllib.parse.quote(str("案件类型:%s" % case_type)))
cookie = self.getCookie(url)
while cookie == 0:
self.setProxyIp()
cookie = self.getCookie(url)
try:
vjkl5 = cookie['vjkl5']
except:
debug("vjk5获取失败，重新获取")
if self.is_change_proxy > 4:
self.setProxyIp()
self.is_change_proxy = 0
else:
self.is_change_proxy = self.is_change_proxy + 1
return self.getUrlAndCookieCaseType(court_name, start_date, end_date, case_type)
try:
post = curlData("http://ws_api.xiezhi.sc.cn/getParam?vjkl5=" + vjkl5)
except:
post = "{}"
debug("post参数获取出错")
post = json.loads(post)
post['Order'] = "法院层级"
post['Page'] = 20
post['number'] = "wens"
post['Direction'] = "asc"
header = {
"User-Agent": getUserAgent(index=self.user_agent_index),
"Origin": "http://wenshu.court.gov.cn"
}
param = {
"vjkl5": vjkl5,
"post": post,
"header": header,
"cookie_all": cookie,
"url": url,
"court_name": court_name,
"start_date": start_date,
"end_date": end_date
}
param['post']['Param'] = "法院名称:%s,裁判日期:%s TO %s,案件类型:%s" % (court_name, start_date, end_date, case_type)
return param
def getYear(self, court_name):
"""
拼装url同时得到cookie
:param court_name:
:return: 所有有数据的年份
"""
# 获取guid
header_1 = {
"User-Agent": getUserAgent(index=self.user_agent_index),
"Origin": "http://wenshu.court.gov.cn"
}
try:
guid = curlData("http://ws_api.xiezhi.sc.cn/getParam?vjkl5=0")
guid = json.loads(guid)
guid = guid['guid']
# number = ""
num_flag = 0
try:
number = curlData("http://wenshu.court.gov.cn/ValiCode/GetCode", {"guid": guid}, header=header_1,
referer="http://wenshu.court.gov.cn",
proxy_ip=self.proxy_ip, timeout=5)
except:
number = "remind"
while number.find("remind") != -1 or number.find("html") != -1 or number.find("服务不可用") != -1:
if num_flag > 4:
self.setProxyIp()
num_flag = 0
else:
num_flag = num_flag + 1
debug("number获取出错，继续获取")
try:
number = curlData("http://wenshu.court.gov.cn/ValiCode/GetCode", {"guid": guid}, header=header_1,
referer="http://wenshu.court.gov.cn",
proxy_ip=self.proxy_ip, timeout=5)
except Exception as e:
debug(e)
sleep(0.5)
except Exception as e:
debug("guid获取出错")
return self.getYear(court_name)
# 拼装url
url = "http://wenshu.court.gov.cn/list/list/?sorttype=1&number=%s&guid=%s&conditions=searchWord+%s+SLFY++%s" % (
number, guid, urllib.parse.quote(str(court_name)), urllib.parse.quote("法院名称:%s" % court_name))
cookie = self.getCookie(url)
while cookie == 0:
self.setProxyIp()
cookie = self.getCookie(url)
try:
vjkl5 = cookie['vjkl5']
except:
debug("vjkl5获取失败，重新获取")
if self.is_change_proxy > 4:
self.setProxyIp()
self.is_change_proxy = 0
else:
self.is_change_proxy = self.is_change_proxy + 1
return self.getYear(court_name)
try:
post = curlData("http://ws_api.xiezhi.sc.cn/getParam?vjkl5=" + vjkl5)
except:
post = "{}"
debug("post参数获取出错")
post = json.loads(post)
post['number'] = number
post['guid'] = guid
header = {
"User-Agent": getUserAgent(index=self.user_agent_index),
"Origin": "http://wenshu.court.gov.cn"
}
post['Param'] = "法院名称:%s" % court_name
year = curlData("http://wenshu.court.gov.cn/List/TreeContent", post, url, cookie, header, self.proxy_ip,
timeout=5)
try:
year = json.loads(year)
year = json.loads(year)
except:
pass
return year[4]['Child']