def cmd5_get_result(self, r_url, r_header, r_data, rps):
if "验证码错误" in rps:
request_img_url = "https://www.cmd5.com/checkcode.aspx/0?" + self.cmd5_repe * "?"
request_img_header = {
"Host": "www.cmd5.com",
"User-Agent":
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept": "image/webp,*/*",
"Accept-Language":
"zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
"Accept-Encoding": "gzip, deflate, br",
"Referer": "https://www.cmd5.com/",
"Connection": "keep-alive",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
"TE": "Trailers"
}
response_img = host.get(url=request_img_url,
headers=request_img_header)
open(self.path + '/img/cimg.gif',
'wb').write(response_img.content) # 将内容写入图片
del response_img
code_demo = Code(img_path=self.path + "/img/cimg.gif",
name="cmd5",
code_num=4,
search_num=1)
code_result = code_demo.get_code()
if self.cmd5_repe > 4:
return 0, "验证码错误"
if code_result["code"] == 0:
self.cmd5_repe += 1
return self.cmd5_get_result(r_url, r_header, r_data, rps)
else:
r_data["ctl00$ContentPlaceHolder1$TextBoxCode"] = code_result[
"result"]
response_md5 = host.post(url=r_url,
headers=r_header,
data=r_data)
html_md5 = HTML(response_md5.text)
text_md5 = html_md5.xpath(
'//*[@id="ctl00_ContentPlaceHolder1_table3"]/tr/td/div/span//text()'
)
self.cmd5_repe += 1
return self.cmd5_get_result(r_url, r_header, r_data, text_md5)
elif rps[0] == "请":
return 0, "需要登录"
else:
return 1, rps[0]
def get_crt(self):
REQ_URL = "https://crt.sh/?q="+self.key
REQ_HEADER = {
"Host": "crt.sh",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
"Accept-Encoding": "gzip, deflate, br",
"Connection": "keep-alive",
"Upgrade-Insecure-Requests": "1",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
}
res = host.get(REQ_URL,REQ_HEADER)
html = HTML(res.text)
crt_shID = xfilter(html.xpath("//table[2]/tr[1]/td/a/text()"))
Summary = xfilter(html.xpath("//table[2]/tr[2]/td/text()"))
self.result["crt_shID"] = crt_shID
self.result["Summary"] = Summary
if not len(crt_shID) and not len(Summary):
print({"value":None})
return ({"value": None})
ct_td_text = "//table[2]/tr[3]/td/div/table/tr/td[1]/table/tr"
Certificate_Transparency = html.xpath(ct_td_text)
ct_th = html.xpath(ct_td_text+"/th/text()")
ct_len = len(Certificate_Transparency)-2
ct_tr_start_num = 3
self.result["Certificate_Transparency"] = get_table(ct_len, ct_tr_start_num, ct_th, html, ct_td_text)
rt_td_text = "//table[2]/tr[4]/td/table/tr"
Revocation = html.xpath(rt_td_text)
rt_th = html.xpath(rt_td_text+"/th/text()")
rt_len = len(Revocation)-1
rt_tr_start_num = 2
self.result["Revocation"] = get_table(rt_len,rt_tr_start_num,rt_th,html,rt_td_text)
rf_td_text = "//table[2]/tr[5]/td/table/tr"
RevoCertificate_Fingerprints= html.xpath(rf_td_text)
rf_th = html.xpath(rf_td_text+"/th/text()")
rf_len = len(RevoCertificate_Fingerprints)
rf_tr_start_num = 1
self.result["RevoCertificate_Fingerprints"] = get_table(rf_len, rf_tr_start_num, rf_th, html, rf_td_text,self.table_gdata)
self.result["Certificate "] = html.xpath("//table[2]/tr[6]/td//text()")
return self.result
def md5_tellyou(self):
request_url = "http://md5.tellyou.top/default.html"
response = host.get(request_url)
html = HTML(response.text)
VIEWSTATE = html.xpath('//*[@id="__VIEWSTATE"]/@value')
VIEWSTATEGENERATOR = html.xpath(
'//*[@id="__VIEWSTATEGENERATOR"]/@value')
EVENTVALIDATION = html.xpath('//*[@id="__EVENTVALIDATION"]/@value')
MD5GET = "正在处理"
request_header = {
"Host": "md5.tellyou.top",
"User-Agent":
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language":
"zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
"Accept-Encoding": "gzip, deflate",
"Referer": "http://md5.tellyou.top/default.html",
"Content-Type": "application/x-www-form-urlencoded",
"Content-Length": "1512",
"Origin": "http://md5.tellyou.top",
"Connection": "keep-alive",
"Upgrade-Insecure-Requests": "1"
}
request_data = {
"__VIEWSTATE": VIEWSTATE,
"__VIEWSTATEGENERATOR": VIEWSTATEGENERATOR,
"__EVENTVALIDATION": EVENTVALIDATION,
"Textmd5": self.Textmd5,
"MD5GET": MD5GET
}
response_md5 = host.post(url=request_url,
headers=request_header,
data=request_data)
html_md5 = HTML(response_md5.text)
md5_text = html_md5.xpath('//td[@class="styleh"]/span[2]//text()')
return 1, md5_text[0]
def get_icp(self):
request_url_1 = "http://icp.chinaz.com/" + self.url_icp_companyName_q
request_header = {
"Host": "icp.chinaz.com",
"User-Agent":
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language":
"zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
"Accept-Encoding": "gzip, deflate",
"Connection": "keep-alive",
"Referer": "http://icp.chinaz.com/" + self.url_icp_companyName_q,
"Upgrade-Insecure-Requests": "1",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
}
response_1 = host.get(url=request_url_1, headers=request_header)
html = HTML(response_1.text)
get_first_id = xfilter(html.xpath('//*[@id="first"]'))
if get_first_id is not None:
company_name = xfilter(
html.xpath('//*[@id="first"]/li[1]/p/a/text()'))
unit_properties = xfilter(
html.xpath('//*[@id="first"]/li[2]/p/strong/text()'))
icp_id = xfilter(
html.xpath('//*[@id="first"]/li[3]/p/font/text()'))
web_name = xfilter(html.xpath('//*[@id="first"]/li[4]/p/text()'))
web_home_isture = xfilter(
html.xpath('//*[@id="first"]/li[5]/span/text()'))
if web_home_isture == "网站负责人":
web_home_url = xfilter(
html.xpath('//*[@id="first"]/li[6]/p/text()'))
verify_time = xfilter(
html.xpath('//*[@id="first"]/li[8]/p/text()'))
else:
web_home_url = xfilter(
html.xpath('//*[@id="first"]/li[5]/p/text()'))
verify_time = xfilter(
html.xpath('//*[@id="first"]/li[7]/p/text()'))
self.result["icp_data"] = {
"company_name": company_name,
"unit_properties": unit_properties,
"icp_id": icp_id,
"web_name": web_name,
"web_home_isture": web_home_isture,
"web_home_url": web_home_url,
"verify_time": verify_time
}
else:
self.result["icp_data"] = None
request_header[
"Accept"] = "application/json, text/javascript, */*; q=0.01"
request_header["Accept-Encoding"] = "gzip, deflate"
request_header[
"Content-Type"] = "application/x-www-form-urlencoded; charset=UTF-8"
request_header["X-Requested-With"] = "XMLHttpRequest"
request_header["Content-Length"] = "13"
request_header["Origin"] = "http://icp.chinaz.com"
request_qiye_url = "http://icp.chinaz.com/Home/QiYeData"
request_qiye_data = {"Kw": self.url_icp_companyName}
response_qiye = host.post(url=request_qiye_url,
data=request_qiye_data,
headers=request_header)
response_qiye_json = json.loads(response_qiye.text)
if response_qiye_json["code"] == 200 and response_qiye_json[
"data"] is not None:
self.result["company_data"] = response_qiye_json["data"]
#获取企业的Icp备案
request_company_icp_url = "http://icp.chinaz.com/Home/PageData"
request_company_icp_data = {
"pageNo": "1",
"pageSize": "10",
"Kw": response_qiye_json["data"]["companyName"]
}
request_header["Content-Length"] = "150"
response_company_icp = host.post(url=request_company_icp_url,
data=request_company_icp_data,
headers=request_header)
response_company_icp_json = json.loads(response_company_icp.text)
if response_company_icp_json["code"] == 200:
self.result["company_other_icp"] = self.get_page_data(
response_company_icp_json["data"], request_company_icp_url,
request_company_icp_data, request_header,
response_company_icp_json['amount'],
response_company_icp_json['pageSize'])
else:
self.result["company_other_icp"] = response_company_icp_json[
"data"]
#获取企业注销的icp
company_delicp_result = {}
request_company_delicp_url = "http://icp.chinaz.com/Home/PageDelData"
request_company_delicp_data = {
"pageNo": "1",
"pageSize": "10",
"Kw": response_qiye_json["data"]["companyName"]
}
response_company_delicp = host.post(
url=request_company_delicp_url,
data=request_company_delicp_data,
headers=request_header)
response_company_delicp_json = json.loads(
response_company_delicp.text)
if response_company_delicp_json["code"] == 200:
self.result["company_delicp"] = self.get_page_data(
response_company_delicp_json["data"],
request_company_delicp_url, request_company_delicp_data,
request_header, response_company_delicp_json['amount'],
response_company_delicp_json['pageSize'])
else:
self.result["company_delicp"] = response_company_delicp_json[
"data"]
else:
self.result["company_data"] = response_qiye_json["data"]
return self.result
def md5_cmd5(self):
request_url = "https://www.cmd5.com/"
response = host.get(request_url)
html = HTML(response.text)
EVENTTARGET_xpath = html.xpath('//*[@id="__EVENTTARGET"]/@value')
EVENTTARGET = EVENTTARGET_xpath[0] if EVENTTARGET_xpath else ""
EVENTARGUMENT_xpath = html.xpath('//*[@id="__EVENTARGUMENT"]/@value')
EVENTARGUMENT = EVENTARGUMENT_xpath[0] if EVENTARGUMENT_xpath else ""
VIEWSTATE_xpath = html.xpath('//*[@id="__VIEWSTATE"]/@value')
VIEWSTATE = VIEWSTATE_xpath[0] if VIEWSTATE_xpath else ""
VIEWSTATEGENERATOR_xpath = html.xpath(
'//*[@id="__VIEWSTATEGENERATOR"]/@value')
VIEWSTATEGENERATOR = VIEWSTATEGENERATOR_xpath[
0] if VIEWSTATEGENERATOR_xpath else ""
InputHashType = "md5"
HiddenField1_xpath = html.xpath(
'//*[@id="ctl00_ContentPlaceHolder1_HiddenField1"]/@value')
HiddenField1 = HiddenField1_xpath[0] if HiddenField1_xpath else ""
HiddenField2_xpath = html.xpath(
'//*[@id="ctl00_ContentPlaceHolder1_HiddenField2"]/@value')
HiddenField2 = HiddenField2_xpath[0] if HiddenField2_xpath else ""
request_data = {
"__EVENTTARGET": EVENTTARGET,
"__EVENTARGUMENT": EVENTARGUMENT,
"__VIEWSTATE": VIEWSTATE,
"__VIEWSTATEGENERATOR": VIEWSTATEGENERATOR,
"ctl00$ContentPlaceHolder1$TextBoxInput": self.Textmd5,
"ctl00$ContentPlaceHolder1$InputHashType": InputHashType,
"ctl00$ContentPlaceHolder1$Button1": "查询",
"ctl00$ContentPlaceHolder1$HiddenField1": HiddenField1,
"ctl00$ContentPlaceHolder1$HiddenField2": HiddenField2
}
request_header = {
"Host": "www.cmd5.com",
"User-Agent":
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language":
"zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
"Accept-Encoding": "gzip, deflate, br",
"Content-Type": "application/x-www-form-urlencoded",
"Content-Length": "2631",
"Origin": "https://www.cmd5.com",
"Connection": "keep-alive",
"Referer": "https://www.cmd5.com/",
"Upgrade-Insecure-Requests": "1"
}
response_md5 = host.post(url=request_url,
headers=request_header,
data=request_data)
html_md5 = HTML(response_md5.text)
text_md5 = html_md5.xpath(
'//*[@id="ctl00_ContentPlaceHolder1_table3"]/tr/td/div/span//text()'
)
result_md5 = self.cmd5_get_result(request_url, request_header,
request_data, text_md5)
return result_md5
def md5_pmd5(self):
request_img_url = "https://api.pmd5.com/pmd5api/checkcode"
res = host.get(url=request_img_url)
if res.status_code == 200:
if len(res.text) < 100: #验证码请求失败
res_text = json.loads(res.text)
return 0, res_text["msg"]
open(self.path + '/img/img.png',
'wb').write(res.content) # 将内容写入图片
code_demo = Code(img_path=self.path + "/img/img.png",
code_num=4,
search_num=3)
code_result = code_demo.get_code()
if self.pmd5_repe > 15:
return 0, "验证码错误"
if code_result["code"] == 0:
time.sleep(1)
self.pmd5_repe += 1
return (self.md5_pmd5())
else:
cookies = res.cookies
cookie = utils.dict_from_cookiejar(cookies)
ck = ""
for k in cookie:
ck += k + "=" + cookie[k] + ";"
del res
request_img_header = {
"accept":
"*/*",
"accept-encoding":
"gzip, deflate, br",
"accept-language":
"zh-CN,zh;q=0.9",
"cookie":
ck,
"origin":
"https://pmd5.com",
"referer":
"https://pmd5.com/",
"sec-fetch-dest":
"empty",
"sec-fetch-mode":
"cors",
"sec-fetch-site":
"same-site",
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36"
}
request_md5_url = "https://api.pmd5.com/pmd5api/pmd5?checkcode=" + code_result[
"result"] + "&pwd=" + self.Textmd5
reponse_md5 = host.get(url=request_md5_url,
headers=request_img_header)
result = json.loads(reponse_md5.text)
if result["code"] == 403:
time.sleep(2)
self.pmd5_repe += 1
return (self.md5_pmd5())
else:
if result["code"] == 0:
return 1, result["result"][self.Textmd5]
else:
return 0, result
else:
return 0, "pmd5_request_error"