def fetch_contact(search_data, resume_id, username, password, proxies=None):
logger.info("start fetch contact with search_data: %s, \nresume_id: %s" % (search_data, resume_id))
user_agent = nautil.user_agent()
logger.info("登录中......")
is_login, session = Login(username, password, user_agent, proxies=proxies).login()
if not is_login:
return {"err_code": 101, "err_msg": session}
ids = []
flag_7002 = False
for resume in GetResume(session, resume_id, search_data, user_agent, proxies=proxies).get_resume_by_keywords():
# print resume["err_msg"]
upload_resume = json.dumps(resume["err_msg"], ensure_ascii=False)
if resume["err_code"] == 7002:
# print json.dumps(resume["err_msg"], ensure_ascii=False)
res = upload(upload_resume, "yifeng", get_contact=True, logger_in=logger)
ids.append(res["resume_id"])
flag_7002 = True
elif resume["err_code"] == 0:
# print json.dumps(resume["err_msg"], ensure_ascii=False)
return upload(upload_resume, "yifeng", get_contact=True, logger_in=logger)
else:
return resume
if flag_7002:
resume_ids = " ".join(ids)
return {"err_code": 7002, "err_msg": "找到了%s个简历, ids: %s" %(len(ids), resume_ids)}
if False:
resume = GetResume(session, resume_id, search_data, user_agent, proxies=proxies).get_resume_by_id()
def fetch_contact_impl(search_data,
resume_id,
user_name,
passwd,
proxies=None,
logger_name=None):
logger.info("登录中.....")
is_login, session = LoginJianLiKa(user_name, passwd,
proxies=proxies).login()
if not is_login:
return session
resume = __get_reusme_by_id(session, resume_id, proxies=proxies)
if resume["err_code"] == 0:
return upload(resume["err_msg"],
"jianlika",
get_contact=True,
logger_in=logger)
if False:
#(备用，使用关键字加上公司名称获取联系方式)
resume = __get_resume_by_keywords(session,
search_data,
resume_id,
proxies=proxies)
if resume["err_code"] == 0:
# print resume["err_msg"]
return upload(resume["err_msg"],
"jianlika",
get_contact=True,
logger_in=logger)
else:
return resume
def fetch_contact_impl(search_data,
resume_id,
username,
password,
user_agent,
proxies=None):
logger.info("登录中......")
is_login, session = Login(username, password, user_agent,
proxies=proxies).login()
if not is_login:
return {"err_code": 101, "err_msg": session}
resume = GetResume(session,
resume_id,
search_data,
user_agent,
proxies=proxies).get_resume_by_id()
if False:
resume = GetResume(session,
resume_id,
search_data,
user_agent,
proxies=proxies).get_resume_by_keywords()
# print resume["err_msg"]
if resume["err_code"] == 0:
return upload(resume["err_msg"],
"lie8",
get_contact=True,
logger_in=logger)
def __fetch_contact(session, resume_id, proxies):
assert isinstance(resume_id, (str, unicode))
encrypt_resume_id = base64.b64encode(str(int(resume_id)))
user_agent = nautil.user_agent()
search_headers = {
"Accept": "application/json, text/javascript, */*; q=0.01",
"User-Agent": user_agent,
"Host": "www.fenjianli.com",
"Origin": "http://www.fenjianli.com",
"Connection": "keep-alive",
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"X-Requested-With": "XMLHttpRequest",
"Referer": "http://www.fenjianli.com/search/detail.htm?ids=%s" %
encrypt_resume_id,
"X-Requested-With": "XMLHttpRequest"
}
logger.info(
'fetching resume detail >> http://www.fenjianli.com/search/detail.htm?ids=%s'
% encrypt_resume_id)
r = session.post('http://www.fenjianli.com/search/getDetail.htm',
headers=search_headers,
proxies=proxies,
data={
'id': resume_id,
'_random': random.random()
})
assert r.status_code == 200, r.status_code
data = json.loads(r.text)
assert 'originalFilePath' in data
logger.info('fetching path %s' % data['originalFilePath'])
raw_headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
"User-Agent": user_agent,
# "Host": "demo.fenjianli.com:9344",
'Upgrade-Insecure-Requests': '1',
}
r = session.get(data['originalFilePath'],
headers=raw_headers,
proxies=proxies)
assert r.status_code == 200, '%s\n%s' % (r.status_code, r.content)
return upload(r.content, 'fjl', get_contact=True, fjl_id=resume_id)
def fetch_contact_impl(search_data,
resume_id,
user_name,
passwd,
proxies=None,
logger_name=None):
if logger_name:
global logger
logger = logging.getLogger(logger_name)
result, session = login(user_name, passwd, proxies=proxies, logger=logger)
if not result:
return session
context = __get_resumes_by_keywords(session, search_data, resume_id)
if context["err_code"] == 101:
logger.error("__get_resumes_by_keywords return None")
return context
elif context["err_code"] == 001:
logger.info("简历ID为智联老ID，但是只搜索到一个简历，下载中.....")
for _resume in __get_resume_url(session, context["err_msg"],
resume_id):
resume = _resume
if resume["err_code"] == 0:
return upload(resume["err_msg"],
"zhaopin",
get_contact=True,
logger_in=logger)
else:
return resume
elif context["err_code"] == 002:
resume_total_num = pq(context["err_msg"]).find(
"div.rd-resumelist-span").find("span").text()
logger.info("简历ID为智联老ID，搜索到简历%s封，下载中....." % resume_total_num)
ids = []
for _resume in __get_resume_url(session,
context["err_msg"],
resume_id,
flag_7002=True):
resume = _resume
if resume["err_code"] == 0:
res = upload(resume["err_msg"],
"zhaopin",
get_contact=True,
logger_in=logger)
_id = res["resume_id"]
ids.append(_id)
resume_ids = " ".join(ids)
return {
"err_code": 7002,
"err_msg": "找到了%s个简历, ids: %s" % (len(ids), resume_ids)
}
else:
logger.info("搜索简历%s成功....." % resume_id)
for _resume in __get_resume_url(session, context["err_msg"],
resume_id):
resume = _resume
if resume["err_code"] == 0:
return upload(resume["err_msg"],
"zhaopin",
get_contact=True,
logger_in=logger)
else:
return resume
def fetch_contact_impl(args,
user_name,
passwd,
proxies=None,
logger_name=None):
if logger_name:
global logger
logger = _logging.getLogger(logger_name)
_timeout = 30
_result, _session = login(user_name, passwd, proxies=proxies)
if not _result:
return _session
result, url = search_resume(_session, args)
if result["err_code"] != 0:
return result
mobile = pq(result["err_msg"]).find("#mobile").text()
email = pq(result["err_msg"]).find("#email").text()
if mobile != '**********' and email != '**********':
logger.info("联系方式已存在，开始上传简历.....")
return upload(result["err_msg"],
"zhuopin",
get_contact=True,
logger_in=logger)
job_id = __get_jobid(_session, proxies=proxies)
if job_id["err_code"] != 0:
return job_id
if "collectresumedownloadbtn" in result["err_msg"]:
logger.info("获取联系方式.....")
post_headers = {
"Accept":
"*/*",
"Accept-Encoding":
"gzip, deflate, br",
"Accept-Language":
"zh-CN,zh;q=0.8",
"Connection":
"keep-alive",
"Origin":
"http://h.highpin.cn",
"Referer":
url,
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
}
seekerUser_id = re.search(r"seekerUserID=(\d+)&resumeID",
url).groups()[0]
resumeid = re.search(r"resumeID=(\d+)&", url).groups()[0]
post_data = {
"seekerUserID": seekerUser_id,
"resumeID": resumeid,
"jobID": job_id["err_msg"],
}
try:
resume_response = _session.post(
"http://h.highpin.cn/ResumeManage/DownLoadResume",
data=post_data,
headers=post_headers,
timeout=_timeout,
proxies=proxies)
assert resume_response
assert resume_response.status_code == 200
except Exception, e:
logger.warning("获取简历ID：%s, 联系方式失败：\n%s" % (re))
return {"err_code": 20019, "err_msg": "获取简历联系方式失败!"}
resume_response.encoding = "utf-8"
if "简历下载已成功，您的职位信息已同时发给该候选人" not in resume_response.text:
logger.warning("获取简历ID%s\n失败,\n%s")
time.sleep(random.uniform(1, 3))
resume = download_resume(_session, url, proxies=proxies)
logger.info("获取联系方式成功，上传简历.....")
return upload(resume["err_msg"],
"zhuopin",
get_contact=True,
logger_in=logger)
def __fetch_contact(session,
resume_id,
user_name,
user_password,
proxies=None):
user_agent = nautil.user_agent()
proxies = None
def __session(method, url, headers={}, data=None):
logger.info('------\nRequesting %s On %s With Data:\n%s\n------' %
(method, url, data))
# time.sleep(random.uniform(4, 15))
time.sleep(random.uniform(1, 2))
assert method in ('get', 'post')
request_headers = {
"User-Agent": user_agent,
}
for k, v in headers.iteritems():
request_headers[k] = v
if method == 'get':
response = session.get(url,
headers=request_headers,
proxies=proxies,
params=data)
if method == 'post':
response = session.post(url,
headers=request_headers,
proxies=proxies,
data=data)
assert response
assert response.status_code == 200
response.encoding = 'utf-8'
return response.text
main_page = __session('get', 'http://www.ganji.com/vip')
if '赶集用户登录' in main_page:
logger.info('cookie fail, try login')
logger.info('re-login')
hash_value = re.search('''window.PAGE_CONFIG.__hash__ = '([^']*)';''',
main_page)
assert hash_value
hash_value = hash_value.group(1)
logger.info('login hash_value:%s' % hash_value)
check_code_url = re.search(
'''<img[^>]*id="login_img_checkcode"[^>]*src=['"]*([^'"]*)['"]*[^>]*>''',
main_page)
assert check_code_url
check_code_url = check_code_url.group(1)
logger.info('login check_code_url:%s' % check_code_url)
time_stamp = str(int(time.time() * 1000))
counter = 0
while True:
counter += 1
if counter > 10:
raise Exception('try too many times to login')
login_result = __session(
'get',
'https://passport.ganji.com/login.php',
headers={
"Host": "passport.ganji.com",
"Referer": "https://passport.ganji.com/login.php?next=/",
"X-Requested-With": "XMLHttpRequest",
"Connection": "keep-alive"
},
data={
"callback":
"jQuery1820229177205394230_%s" % time_stamp,
"username":
user_name,
"password":
user_password,
"checkCode":
parse_check_code(session, check_code_url, 'ganji',
proxies),
"setcookies":
"14",
"second":
"",
"parentfunc":
"",
"redirect_in_iframe":
"",
"next":
'/',
"__hash__":
hash_value,
"_":
time_stamp
})
open(session.temp_folder + os.path.sep + 'login_result.html',
'w').write(login_result)
if 'error_msg' in login_result:
logger.warning('login fail with response:\n%s' % login_result)
else:
break
logger.info('trying to buy contact')
message = __session('get',
'http://www.ganji.com/findjob/download_resume.php',
headers={
"Host": "www.ganji.com",
"Referer":
"http://www.ganji.com/jianli/%sx.htm" % resume_id,
"Upgrade-Insecure-Requests": 1,
},
data={
"source": "detail",
"resume_type": "0",
"findjob_puid": resume_id,
"job_postion": "",
"callback": "show_contact",
"is_batch_view_resume": 0
})
open(session.temp_folder + os.path.sep + 'message.html',
'w').write(message)
if '您已下载过该简历' not in message:
if '简历下载数不足' in message:
raise Exception('The Ganji Account Can Not Afford this Resumes')
elif '此帖子已删除' in message:
raise Exception('The Ganji Resume Deleted')
else:
assert '确认查看' in message
buy_url = 'http://www.ganji.com/findjob/download_resume.php?source=detail&resume_type=0&findjob_puid=%s&job_postion=&callback=show_contact&is_batch_view_resume=0' % resume_id
tel_message = __session('post',
buy_url,
headers={
"Host": "www.ganji.com",
"Origin": "http://www.ganji.com",
"Referer": buy_url,
"Upgrade-Insecure-Requests": 1,
},
data={"one_key_download_setting": 1})
assert 'tel-code' in tel_message
logger.info('buy contact done, try upload resume')
resume = __session('get',
'http://www.ganji.com/jianli/%sx.htm' % resume_id)
shutil.rmtree(session.temp_folder)
return upload(resume, 'ganji', get_contact=True)
def fetch_contact_impl(resume_id,
user_name,
passwd,
proxies=None,
logger_name=None):
if logger_name:
global logger
logger = logging.getLogger(logger_name)
__timeout = 30
# proxies = {'http': 'http://120.26.80.194:60762', 'https': 'http://120.26.80.194:60762'}
user_agent = nautil.user_agent()
result, session = login(user_name, passwd, proxies=proxies)
if not result:
return session
session.temp_folder = os.path.join(tempfile.gettempdir(), "naren",
str(random.randint(1, 10000)))
if not os.path.isdir(session.temp_folder):
os.makedirs(session.temp_folder)
result = __fet_contanct(session, resume_id, user_agent, proxies=proxies)
if result["err_code"] != 0:
return result
url = "http://ehire.51job.com/%s" % result["err_msg"]
resume_page_result = __get_resume_page(session, url, proxies=proxies)
if resume_page_result["err_code"] != 0:
return resume_page_result
resume_page_text = resume_page_result["err_msg"]
tel_mail = pq(resume_page_text).find(".infr").text()
if u"电 话：" in resume_page_text and u"E-mail：" in resume_page_text:
logger.info("简历联系方式已存在")
shutil.rmtree(session.temp_folder)
return upload(resume_page_text,
"j51",
get_contact=True,
logger_in=logger)
if "*" not in tel_mail:
logger.info("简历联系方式已存在")
shutil.rmtree(session.temp_folder)
return upload(resume_page_text,
"j51",
get_contact=True,
logger_in=logger)
is_download = pq(resume_page_text).find(
".btn_down[id=UndownloadLink]").attr("onclick")
if not is_download:
logger.warning("当前账号没有下载权限，获取简历页失败")
return {"err_code": 101, "err_msg": "当前账号没有下载权限！"}
if u"点击查看联系方式！" in resume_page_text and u"简历信息" in resume_page_text:
post_data = {
"doType": "SearchToCompanyHr",
"userId": resume_id,
"strWhere": "",
}
post_headers = {
"Accept": "application/xml, text/xml, */*",
"Accept-Encoding": "gzip,deflate",
"Content-Type": "application/x-www-form-urlencoded",
"Accept-Language": "zh-CN,zh;q=0.8",
"Cache-Control": "max-age=0",
"Connection": "keep-alive",
"Host": "ehire.51job.com",
"Origin": "http://ehire.51job.com",
"Referer": url,
"X-Requested-With": "XMLHttpRequest",
}
logger.info("获取简历详情......")
resume_text = session.post(
url="http://ehire.51job.com/Ajax/Resume/GlobalDownload.aspx",
headers=post_headers,
data=post_data,
timeout=__timeout,
proxies=proxies)
if u"不属于以上地区" in resume_text.text:
return {
"err_code":
20022,
"err_msg":
"对不起，您暂时不能下载该份简历，原因是：您选中的简历中存在应聘者所在地超出合同范围的情况。请核实您的情况，若有疑问请与销售或客服人员联系。"
}
if resume_text.status_code != 200:
return {"err_code": 20019, "err_msg": "获取简历失败"}
resume_text.encoding = "utf-8"
resume_result = __get_resume_page(session, url, proxies=proxies)
logger.info('fetch resume_id %s done, try upload resume' % resume_id)
shutil.rmtree(session.temp_folder)
return upload(resume_result["err_msg"],
"j51",
get_contact=True,
logger_in=logger)
else:
return {"err_code": 20020, "err_msg": "抱歉，没有搜到您想找的简历！"}
def __fetch_contact(session,
resume_id,
user_name,
user_password,
proxies=None):
user_agent = nautil.user_agent()
proxies = None
def __session(method, url, headers={}, data=None):
logger.info('------\nRequesting %s On %s With Data:\n%s\n------' %
(method, url, data))
time.sleep(random.uniform(4, 15))
assert method in ('get', 'post')
assert method == 'post' or not data
request_headers = {
"User-Agent": user_agent,
"Origin": "http://jianli.58.com",
}
for k, v in headers.iteritems():
request_headers[k] = v
if method == 'get':
response = session.get(url,
headers=request_headers,
proxies=proxies)
if method == 'post':
response = session.post(url,
headers=request_headers,
proxies=proxies,
data=data)
assert response
assert response.status_code == 200
response.encoding = 'utf-8'
return response.text
main_page = __session('get', 'http://my.58.com/index')
if '普通登录方式' in main_page:
logger.info('cookie fail, try login')
# login_cookies = get_cookie('x58', user_name)
login_cookies = __login(user_name,
user_password,
user_agent,
proxies=proxies)
assert isinstance(login_cookies, list)
login_cookie_jar = requests.cookies.RequestsCookieJar()
for login_cookie in login_cookies:
login_cookie_jar.set(login_cookie['name'],
login_cookie['value'],
domain=login_cookie['domain'],
path=login_cookie['path'])
session.cookies.update(login_cookie_jar)
message = __session(
'get', 'http://jianli.58.com/resumemsg/?resumeid=%s&rand_code=%s&f=' %
(resume_id, random.random()))
if '您好，此求职者只允许在58同城认证营业执照的企业查看和下载' in message:
raise Exception('Need Certification of Business Licence')
if '您可直接查看本简历' not in message:
remain = re.search(
ur"""您目前共有 <span class='f-f1a'>(\d+)</span> 份简历可下载""", message)
assert remain and remain.group(
1).isdigit(), 'Unexpected Message \n%s' % message
remain = int(remain.group(1))
if remain < 5:
raise Exception(
'The 58 Accoun Remains Only %s Resumes To Download' % remain)
logger.info("获取联系方式.....")
tel = __session(
'get',
'http://jianli.58.com/ajax/resumemsg/?operate=userdown&rid=%s' %
resume_id,
headers={
"Referer":
"http://jianli.58.com/resumemsg/?resumeid=%s&rand_code=%s&f=" %
(resume_id, random.random())
})
open(session.temp_folder + os.path.sep + 'tel.html', 'w').write(tel)
if '您可直接查看本简历' not in tel:
assert re.search('>([\d ]*)</span',
tel), 'TEL NOT FOUND in html:\n%s' % tel
# tel = tel.group(1).replace(' ', '')
logger.info('fetch done, try upload resume')
resume = __session('get', 'http://jianli.58.com/resume/%s/' % resume_id)
open(session.temp_folder + os.path.sep + 'resume.html', 'w').write(resume)
shutil.rmtree(session.temp_folder)
return upload(resume, 'x58', get_contact=True)