def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.title = user.get("title", "")
# print chardet.detect(self.title)
self.title = urllib.quote(self.title.encode('utf8'))
self.project_district = user.get("project_district")
self.project_developer_name_value = user.get("project", "")
self.date_filter_min = user.get("date_filter_min","")
self.date_filter_max = user.get("date_filter_max","")
# print self.title,self.project_developer_name_value,self.project_district,self.date_filter_max,self.date_filter_min
# self.title = urllib.quote(self.title.decode(sys.stdin.encoding).encode('utf-8'))
# self.project_district = urllib.quote(self.project_district.decode(sys.stdin.encoding).encode('utf8'))
# self.project_developer_name_value = urllib.quote(self.project_developer_name_value.decode(sys.stdin.encoding).encode('utf8'))
# self.date_filter_min = urllib.quote(self.date_filter_min.decode(sys.stdin.encoding).encode('utf8'))
# self.date_filter_max = urllib.quote(self.date_filter_max.decode(sys.stdin.encoding).encode('utf8'))
#
self.token = user.get("token", "")
self.userid = user.get("userid", "")
self.LoginUrl = "https://newhouse.cnnbfdc.com"
self.result = user.get("result", "")
self.GJJInfo = []
self.bild = []
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.fpjy = user.get("fpjy", "")
self.fpdm = user.get("fpdm", "")
self.fphm = user.get("fphm", "")
self.kprq = user.get("kprq", "")
self.fpje = user.get("fpje", "")
self.token = user.get("token", "")
self.userid = user.get("userid", "")
self.fpdm_area = self.fpdm[0:4]
self.fpdm_url = AREA.get(self.fpdm_area, "")
self.suiji = str(int(round(time.time() * 1000)))
self.codeUrl = self.fpdm_url + '/WebQuery/yzmQuery?callback=jQuery110204713398352365614_' + self.suiji + '&fpdm=' + self.fpdm + '&r=' + str(
'%.16f' %
(random.random())) + '&v=V1.0.04_001' + '&nowtime=' + str(
int(round(time.time() * 1000))
) + '&publickey=B8EE27C2CFEABABBD1DB92F4D84E4EA3&_=' + str(
int(round(time.time() * 1000)))
self.result = user.get("result", "")
self.GJJInfo = []
self.PerInfo = {}
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.username = urllib.quote(user.get("name", ""))
self.idcard = urllib.quote(user.get("idcard", ""))
self.area = urllib.quote(user.get("area", ""))
self.token = user.get("token", "")
self.userid = user.get("userid", "")
# urllib.quote(a)
self.LoginUrl = "https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?" + "resource_id=6899&query=%E5%A4%B1%E4%BF%A1%E8%A2%AB%E6%89%A7%E8%A1%8C%E4%BA%BA%E5%90%8D%E5%8D%95&cardNum=" + self.idcard + "&iname=" + self.username + "&areaName=" + self.area + "&ie=utf-8&oe=utf-8&format=json&t=" + str(
int(round(time.time() *
1000))) + "&cb=jQuery110207690611877233657_" + str(
int(round(time.time() * 1000))) + "&_=" + str(
int(round(time.time() * 1000)))
self.result = user.get("result", "")
self.GJJInfo = []
self.PerInfo = {}
self.PayRecord = {}
def __init__(self):
"""
初始化
:param spider:
:return:
"""
# 线程数
self.thread_num = THREAD_NUM
# 队列数：1
self.thread_q_size = THREAD_Q_SIZE
# redis操作类
self.redisUtils = RedisUtils()
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.keyword = user.get("keyword", "")
# self.gjjaccnum = self.username if len(self.username) <= 15 else ""
# self.pwd = user.get("password", "")
self.age = FANGAGE.get(user.get('age',''),'') or FANGAGE.get(user.get('year',''), '')
self.token = user.get("token", "")
self.flower = LOUCENG.get(user.get('flower',''),'') or LOUCENG.get(user.get('floor',''),'')
self.hu_type = HUXING.get(user.get('hu_type',''),'') or HUXING.get(user.get('housetype',''),'')
# self.userid = user.get("userid", "")
self.startUrl = "http://esf.nb.fang.com/NewSecond/sale_info/searchlist_new2014.aspx"
self.hostUrl = "http://esf.nb.fang.com/"
self.result = user.get("result", "")
self.GJJInfo = []
def threadWork(t):
"""
进程工作，用来启动多个线程
:param x:
:return:
"""
redisUtils = RedisUtils()
thread_pool = ThreadPool(THREAD_NUM * 10, q_size=THREAD_Q_SIZE)
dict_json = redisUtils.getCons()
logger.debug("Now have tasks -> " + str(dict_json))
if dict_json != []:
try:
for i in dict_json:
spider_name = re.findall('spider_(.*):task', i)[0]
# for i in [i.split(":")[0] for i in dict_json]:
requests = makeRequests(imptask, [spider_name])
thread_pool.putRequest(requests[0])
thread_pool.wait()
except Exception as e:
logger.error(e)
else:
time.sleep(1)
def __init__(self, dict_json, key=[], verifycode_type='png'):
self.redisUtils = RedisUtils()
self.damatuWeb = damatuWeb
self.PROXYADDR = PROXYADDR
self.dict_json = dict_json
self.token = self.dict_json['token']
self.verifycode_type = verifycode_type
self.status = None
self.desc = None
self.current_milli_time = lambda: str(int(round(time.time() * 1000)))
self.startTime = self.current_milli_time()
self.realpath = os.path.split(os.path.realpath(__file__))[0]
filename = 'verifycode/%s_verifycode.%s' % (self.startTime,
verifycode_type)
self.code_path = os.path.join(self.realpath, filename)
logging.config.fileConfig('unicom/logging.config')
self.logger = logging.getLogger('flow')
# 是否保存用户目录，默认为爬虫出错才保存，也可以手动修改
self.rmuserdirFlag = False
self.mkUserdir(key)
class SpiderClient():
def __init__(self):
"""
初始化
:param spider:
:return:
"""
# 线程数
self.thread_num = THREAD_NUM
# 队列数：1
self.thread_q_size = THREAD_Q_SIZE
# redis操作类
self.redisUtils = RedisUtils()
def progressWork(self):
"""
进程工作，用来启动多个线程
:param x:
:return:
"""
thread_pool = ThreadPool(self.thread_num, q_size=self.thread_q_size)
for i in range(self.thread_num):
dict_t = {}
requests = makeRequests(self.threadWork, [dict_t])
thread_pool.putRequest(requests[0])
thread_pool.wait()
# def threadWork(self, t):
def threadWork(self):
"""
线程工作的方法，主要用户获取任务
:param t:
:return:
"""
startTime = datetime.now()
logger.info('开始等待获取任务')
while True:
try:
# 从任务队列中获取任务数据
dict_json = self.redisUtils.getCon(SOURCE)
if dict_json is not None:
dict_json = decryptKwargs(dict_json)
name = dict_json['token']
# 将token放入到thread中
logger.info("获取到任务,%s" % name)
# sendMail(u"邮件log测试",'*****@*****.**')
dict_json.update({"result": []})
self.taskWork(dict_json)
break
else:
finishTime = datetime.now()
# abs():返回数字的绝对值
if abs(finishTime.minute - startTime.minute) >= WAITTING:
break
time.sleep(1)
except Exception:
s = traceback.format_exc()
logger.error(s)
@Time()
def taskWork(self, dict_json):
"""
具体任务的工作方法,主要调用爬虫完成数据爬取
:param dict_json:
:return:
"""
# token = dict_json['token']
try:
client = SpiderMain(dict_json)
f = client.crawl()
logger.info('任务结束：%s' % dict_json['token'])
# 抓取成功则删除所保存的样本，如需保存可在爬虫中返回Ture
if not f:
client.rmUserdir(client.userdir)
# logger.info("不需要抓取图片验证码,token:%s" % token)
# p1 = threading.Thread(target=client.crawl, args=("user",))
# p2 = threading.Thread(target=client.crawl)
# p1.start()
# p2.start()
except Exception:
self.redisUtils.setNotify(token=dict_json['token'],
val='2',
decs='爬虫爬取失败')
s = traceback.format_exc()
logger.error(s)
logger.info('任务结束：%s' % dict_json['token'])
def __init__(self, user):
self.url_area = {
"北京": "http://bj.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml",
"天津": "http://tj.gsxt.gov.cn/index.html",
"河北": "http://he.gsxt.gov.cn/notice/",
"山西": "http://sx.gsxt.gov.cn/index.jspx",
"内蒙古": "http://nm.gsxt.gov.cn:58888/",
"辽宁": "http://ln.gsxt.gov.cn/saicpub/",
"吉林": "http://jl.gsxt.gov.cn/",
"黑龙江": "http://hl.gsxt.gov.cn/index.jspx",
"上海": "http://sh.gsxt.gov.cn/notice",
"江苏": "http://www.jsgsj.gov.cn:58888/province/",
"浙江": "http://zj.gsxt.gov.cn/client/entsearch/toEntSearch",
"安徽": "http://ah.gsxt.gov.cn/index.jspx",
"福建": "http://fj.gsxt.gov.cn/notice",
"江西": "http://jx.gsxt.gov.cn/",
"山东": "http://sd.gsxt.gov.cn/",
"广东": "http://gd.gsxt.gov.cn/",
"广西": "http://gx.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml",
"海南": "http://hi.gsxt.gov.cn/index.jspx",
"河南": "http://ha.gsxt.gov.cn/index.jspx",
"湖北": "http://hb.gsxt.gov.cn/index.jspx",
"湖南": "http://hn.gsxt.gov.cn/notice/",
"重庆": "http://cq.gsxt.gov.cn/",
"四川": "http://sc.gsxt.gov.cn/notice/",
"贵州": "http://gz.gsxt.gov.cn/",
"云南": "http://yn.gsxt.gov.cn/notice/",
"西藏": "http://xz.gsxt.gov.cn/index.jspx",
"陕西": "http://sn.gsxt.gov.cn/ztxy.do?method=index&random=",
"甘肃": "http://gs.gsxt.gov.cn/gsxygs/",
"青海": "http://qh.gsxt.gov.cn/index.jspx",
"宁夏": "http://nx.gsxt.gov.cn/",
"新疆": "http://xj.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml"
}
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.area = user.get("area", "")
self.keyword = user.get("idCard", "")
self.token = user.get("token", "")
self.LoginUrl = self.url_area.get(
self.area,
"") if self.area else "http://www.gsxt.gov.cn/index.html"
self.result = user.get("result", "")
self.GJJInfo = []
self.br = self.get_webdriver("chrome")
self.br.dc = DriverClean(1, time.time(), self.br.service.process.pid,
self.br)
self.br.get1 = MethodType(get1, self.br, webdriver.Chrome)
self.br.find_element_by_xpath1 = MethodType(find_element_by_xpath1,
self.br, webdriver.Chrome)
global globallogger
globallogger = self.logger
# self.br.maximize_window()
# self.br.set_window_size(1300,900)
# self.proxy = self._proxy()
# proxy=webdriver.Proxy()
# proxy.proxy_type=ProxyType.MANUAL
# proxy.http_proxy=self.proxy
# 将代理设置添加到webdriver.DesiredCapabilities.PHANTOMJS中
# proxy.add_to_capabilities(self.dcap)
# self.br.start_session(self.dcap)
# self.br.get('http://httpbin.org/ip')
# print self.br.page_source
self.wait = WebDriverWait(self.br, 10, 0.5)
self.br.set_page_load_timeout(10)
self.br.set_script_timeout(15)
self.br.implicitly_wait(10)
class SpiderMain(hypc_accumulation_fund):
logger = logging.getLogger()
def __init__(self, user):
self.url_area = {
"北京": "http://bj.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml",
"天津": "http://tj.gsxt.gov.cn/index.html",
"河北": "http://he.gsxt.gov.cn/notice/",
"山西": "http://sx.gsxt.gov.cn/index.jspx",
"内蒙古": "http://nm.gsxt.gov.cn:58888/",
"辽宁": "http://ln.gsxt.gov.cn/saicpub/",
"吉林": "http://jl.gsxt.gov.cn/",
"黑龙江": "http://hl.gsxt.gov.cn/index.jspx",
"上海": "http://sh.gsxt.gov.cn/notice",
"江苏": "http://www.jsgsj.gov.cn:58888/province/",
"浙江": "http://zj.gsxt.gov.cn/client/entsearch/toEntSearch",
"安徽": "http://ah.gsxt.gov.cn/index.jspx",
"福建": "http://fj.gsxt.gov.cn/notice",
"江西": "http://jx.gsxt.gov.cn/",
"山东": "http://sd.gsxt.gov.cn/",
"广东": "http://gd.gsxt.gov.cn/",
"广西": "http://gx.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml",
"海南": "http://hi.gsxt.gov.cn/index.jspx",
"河南": "http://ha.gsxt.gov.cn/index.jspx",
"湖北": "http://hb.gsxt.gov.cn/index.jspx",
"湖南": "http://hn.gsxt.gov.cn/notice/",
"重庆": "http://cq.gsxt.gov.cn/",
"四川": "http://sc.gsxt.gov.cn/notice/",
"贵州": "http://gz.gsxt.gov.cn/",
"云南": "http://yn.gsxt.gov.cn/notice/",
"西藏": "http://xz.gsxt.gov.cn/index.jspx",
"陕西": "http://sn.gsxt.gov.cn/ztxy.do?method=index&random=",
"甘肃": "http://gs.gsxt.gov.cn/gsxygs/",
"青海": "http://qh.gsxt.gov.cn/index.jspx",
"宁夏": "http://nx.gsxt.gov.cn/",
"新疆": "http://xj.gsxt.gov.cn/sydq/loginSydqAction!sydq.dhtml"
}
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.area = user.get("area", "")
self.keyword = user.get("idCard", "")
self.token = user.get("token", "")
self.LoginUrl = self.url_area.get(
self.area,
"") if self.area else "http://www.gsxt.gov.cn/index.html"
self.result = user.get("result", "")
self.GJJInfo = []
self.br = self.get_webdriver("chrome")
self.br.dc = DriverClean(1, time.time(), self.br.service.process.pid,
self.br)
self.br.get1 = MethodType(get1, self.br, webdriver.Chrome)
self.br.find_element_by_xpath1 = MethodType(find_element_by_xpath1,
self.br, webdriver.Chrome)
global globallogger
globallogger = self.logger
# self.br.maximize_window()
# self.br.set_window_size(1300,900)
# self.proxy = self._proxy()
# proxy=webdriver.Proxy()
# proxy.proxy_type=ProxyType.MANUAL
# proxy.http_proxy=self.proxy
# 将代理设置添加到webdriver.DesiredCapabilities.PHANTOMJS中
# proxy.add_to_capabilities(self.dcap)
# self.br.start_session(self.dcap)
# self.br.get('http://httpbin.org/ip')
# print self.br.page_source
self.wait = WebDriverWait(self.br, 10, 0.5)
self.br.set_page_load_timeout(10)
self.br.set_script_timeout(15)
self.br.implicitly_wait(10)
# 加入当次代理
# self.proxy = self._proxy()
def _proxy(self):
proxy = self.session.get(self.PROXYADDR).content
# return {"http": "http://" + proxy, "https": "http://" + proxy}
return proxy
def run(self, keyword):
content = self.hack_geetest(keyword.decode('utf8'))
if not content[0].get("base_info", "") and not content[0].get(
"admin_penalty_info", ""
) and not content[0].get(
"operate_abnormal_info", ""
) and not content[0].get("key_person_info", "") and not content[0].get(
"change_info", "") and not content[0].get(
"check_info", "") and not content[0].get(
"chattel_info", "") and not content[0].get(
"branch_info", "") and not content[0].get(
"equity_pledged_info",
"") and not content[0].get(
"Shareholder_info",
"") and not content[0].get(
"judicial_assist_info",
"") and not content[0].get(
"knowledge_info",
"") and not content[0].get(
"brand_info",
"") and not content[0].get(
"annual_shareholder_info",
"") and not content[0].get(
"annual_info", ""):
self.status = PASSWORD_IS_NULL
self.quit_webdriver()
return content
def wait_for(self, by1, by2):
self.br.dc.setts(time.time())
self.br.dc.setstatus(0)
return self.wait.until(EC.presence_of_element_located((by1, by2)))
def input_params(self, name):
self.logger.info('正在打开官网URL')
try:
self.br.get1(self.LoginUrl)
# self.br.refresh()
except Exception as e:
self.logger.error(e)
try:
# 防止再次刷新的时候出现卡死,所以没用热刷新的方式
self.br.get1(self.br.current_url)
except Exception as f:
self.logger.error(f)
self.logger.info('已经进入官网')
ui.WebDriverWait(self.br, 10).until(
EC.visibility_of_element_located(
(By.XPATH, '//*[@id="btn_query"]')))
element = self.wait_for(By.ID, "keyword")
element.send_keys(name)
element = self.wait_for(By.ID, "btn_query")
element.click()
self.status = CRAWL_SUCCESS
def _save_captcha(self, codeurl):
"""
下载验证码，返回图片b64编码，
"""
self.logger.info("刷新验证码")
try:
codeContent = self.session.get(codeurl, headers=IMGHEADERS).content
self.logger.debug("验证码二进制内容：{0}".format(codeContent)[:50])
self.logger.info("下载验证码")
self.status = NEED_BCODE
with open(
os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/"), 'wb') as f:
f.write(codeContent)
self.logger.info("验证码图片已保存!")
bcode = base64.b64encode(codeContent)
self.status = CRAWL_SUCCESS
return bcode
except:
s = traceback.format_exc()
self.logger.error("刷新验证码错误：%s" % s)
self.status, self.desc = BCODE_IS_NULL, BCODE_IS_NULL_DESC
# return {"error": "超时或代码异常"}
def quit_webdriver(self):
self.br.quit()
self.br.dc.setterm(1)
def get_webdriver(self, name):
'''选择爬取的方式'''
try:
if name.lower() == "phantomjs":
self.dcap = dict(DesiredCapabilities.PHANTOMJS)
self.dcap[
"phantomjs.page.customHeaders.User-Agent"] = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36"
self.status = CRAWL_SUCCESS
return webdriver.PhantomJS(desired_capabilities=self.dcap)
elif name.lower() == "chrome":
display = Display(visible=0, size=(1920, 1080))
display.start()
self.status = CRAWL_SUCCESS
# return webdriver.Chrome("/usr/local/bin/chromedriver")
return webdriver.Chrome()
elif name.lower() == "firefox":
display = Display(visible=0, size=(1920, 1080))
display.start()
self.status = CRAWL_SUCCESS
return webdriver.Firefox()
except Exception as e:
self.logger.error('运行无头浏览器错误')
self.status, self.decs = PASSWORD_IS_NULL, PASSWORD_IS_NULL_DESC
def get_bcode(self):
'''获取从redis中获取的坐标值'''
self.startTime = datetime.now()
while True:
self.logger.info(u'等待用户传入坐标')
inputValue = self.redisUtils.getNotify(self.token, 'bcode')
if inputValue:
coordinate = self.prase_bcode(inputValue)
self.redisUtils.DelNotify(self.token, "bcode")
return coordinate
else:
self.finishTime = datetime.now()
tail_time = self.finishTime - self.startTime
if tail_time.total_seconds() > 120:
self.logger.info('接收用输入超时:%s' % self.token)
self.desc = '接收用户输入超时'
time.sleep(1)
break
time.sleep(1)
def prase_bcode(self, zuobiao):
'''坐标处理'''
try:
zuobiao_list1 = zuobiao.split('_')
zuobiao_list = zuobiao_list1[1:]
len_zuobiao = len(zuobiao_list) / 2
coordinate = []
for num in range(len_zuobiao):
list_n = []
list_n.append(zuobiao_list[2 * num])
list_n.append(zuobiao_list[2 * num + 1])
coordinate.append(list_n)
self.status = CRAWL_SUCCESS
return coordinate
except Exception as e:
self.logger.error('处理坐标异常: %s' % e)
self.status = IDCARD_ERROR
return ''
def element_click(self, coor):
'''模拟依次点击'''
try:
if coor and self.br.find_element_by_class_name("geetest_item_img"):
for i in range(len(coor)):
element = self.br.find_element_by_class_name(
"geetest_item_img")
ActionChains(self.br).move_to_element_with_offset(
to_element=element,
xoffset=int(coor[i][0]) - 7,
yoffset=int(coor[i][1]) - 5).perform()
ActionChains(self.br).click().perform()
time.sleep(0.8)
element_cli = self.wait_for(By.CLASS_NAME,
"geetest_commit_tip")
element_cli.click()
time.sleep(0.5)
element = self.wait_for(By.CLASS_NAME, "geetest_result_tip")
ans = element.text.encode("utf-8")
self.status = CRAWL_SUCCESS
return ans
else:
self.logger.info('暂无图片点击')
return '失败'
except Exception as e:
self.logger.error('破解验证码失败')
self.status = PASSWORD_ERROR
def click_pic(self, info):
'''获取图片,将图片的base64发送给服务或第三方来处理'''
self.logger.info('需要用户提供点击操作')
try:
ima_url = ifNotEmptyGetIndex(
info.xpath("//*[@class='geetest_item_img']/@src"))
card_base = self._save_captcha(ima_url)
Data = {
'token': self.token,
'img_base64': card_base,
'spider_name': 'gsxt',
'userid': 'yinzhouyinhang'
}
content = self.session.post(url='http://127.0.0.1:8000/img',
data=Data).content
content = eval(content)
url_imag = content.get("result", "")
self.decs = '请输入url,请求图片并点击'
redis_dict = {
"image_url": url_imag,
"image_base64": "data:image/jpg;base64," + card_base,
"token": self.token
}
self.redisUtils.setNotify(token=self.token,
val="1",
decs=self.decs,
result=redis_dict)
self.br.dc.setstatus(1)
self.br.dc.setts(time.time())
self.logger.info("begin wait bcode....")
co_ordinate = self.get_bcode()
self.logger.info("begin set status....")
self.br.dc.setstatus(0)
self.br.dc.setts(time.time())
ans = self.element_click(co_ordinate)
return ans
except Exception as e:
self.logger.error(e)
self.status = CRAWL_SUCCESS
def hack_geetest(self, company='大连火眼征信管理有限公司北京'):
'''爬取的流程'''
try:
self.input_params(company)
for i in range(10):
self.logger.info(u'开始判断验证码的类型')
time.sleep(1)
info = etree.HTML(str(self.br.page_source))
if info.xpath("//*[@class='geetest_item_img']/@src"):
for j in range(3):
info2 = etree.HTML(str(self.br.page_source))
ans = self.click_pic(info2)
self.logger.info('破解验证码结果: %s' % ans)
if '成功' in ans:
ui.WebDriverWait(self.br, 10).until(
EC.visibility_of_element_located(
(By.XPATH,
'//*[@class="search_result_span1"]')))
self.status = CRAWL_SUCCESS
return country1(self.br).data()
elif '失败' in ans and j < 2:
time.sleep(3)
self.logger.info('图片验证点击失败')
self.status = BCODE_ERROR
elif '失败' in ans and j == 2:
self.logger.info('最后一次图片验证点击失败')
self.status = BCODE_ERROR
return
else:
self.logger.info('图片验证点击失败,正在重新请求')
self.status = BCODE_ERROR
elif info.xpath(
"//*[@class='geetest_slider_track']/div/text()"):
self.logger.info('系统正在重试')
self.input_params(company)
else:
time.sleep(2)
info = etree.HTML(str(self.br.page_source))
if info.xpath("//*[@class='ads-right']/div[1]/div/text()"):
self.status = CRAWL_SUCCESS
return country1(self.br).data()
else:
self.logger.info('尝试再次访问')
time.sleep(1)
self.input_params(company)
except Exception as e:
self.logger.error('智能检测程序错误%s' % e)
self.status = CRAWL_FAIL
# return e
def login(self, flag):
if self.area == '陕西':
millis = int(round(time.time() * 1000))
self.LoginUrl = self.LoginUrl + str(millis)
try:
content = self.run(self.keyword)
return content
except Exception as e:
self.status = CRAWL_FAIL
self.logger.error('抓取错误：%s' % e)
@Time()
def crawl(self, flag=""):
CurTime = datetime.now().strftime("%Y-%m-%d")
PastTime = (datetime.now() - timedelta(days=729)).strftime("%Y-%m-%d")
try:
content = self.login(flag)
self.GJJInfo.append(content)
self.result.append(self.GJJInfo[0])
except:
s = traceback.format_exc()
self.logger.error("抓取错误：%s" % s)
self.status, self.desc = self.status, PROGRAM_ERROR_DESC
finally:
try:
if len(self.result) == 1 and self.status == CRAWL_SUCCESS:
self.desc = CRAWL_SUCCESS_DESC
result_json = json.dumps(self.result[0],
ensure_ascii=False)
print result_json
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val="1",
decs="抓取成功！",
result=result_json)
elif self.status == CRAWL_FAIL:
self.desc = CRAWL_FAIL_DESC
elif self.status == CRAWL_TIMEOUT:
self.desc = CRAWL_TIMEOUT_DESC
elif self.status == IDCARD_ERROR:
self.desc = IDCARD_ERROR_DESC
elif self.status == PASSWORD_ERROR:
self.desc = PASSWORD_ERROR_DESC
elif self.status == BCODE_ERROR:
self.desc = BCODE_ERROR_DESC
elif self.status == PASSWORD_IS_NULL:
self.desc = PASSWORD_IS_NULL_DESC
else:
self.desc = PROGRAM_ERROR_DESC
except Exception as e:
s = traceback.format_exc()
self.logger.error(s)
finally:
try:
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val=self.status,
decs=self.desc)
except Exception:
s = traceback.format_exc()
self.logger.error(s)
def zipToStr(self, content):
'''
使用urllib2获取到的内容被压缩，需要进行解压缩
:param content: 需要解压的内容
:return:
'''
try:
conn = zlib.decompress(content, 16 + zlib.MAX_WBITS)
return conn
except:
self.logger.error('解压缩响应内容出错%s' % traceback.format_exc())
raise Exception("解压缩响应内容出错%s" % traceback.format_exc())
class SpiderClient():
def __init__(self):
"""
初始化
:param spider:
:return:
"""
# 线程数
self.thread_num = THREAD_NUM
# 队列数：1
self.thread_q_size = THREAD_Q_SIZE
# redis操作类
self.redisUtils = RedisUtils()
def progressWork(self):
"""
进程工作，用来启动多个线程
:param x:
:return:
"""
thread_pool = ThreadPool(self.thread_num, q_size=self.thread_q_size)
for i in range(self.thread_num):
dict_t = {}
requests = makeRequests(self.threadWork, [dict_t])
thread_pool.putRequest(requests[0])
thread_pool.wait()
def threadWork(self, t):
"""
线程工作的方法，主要用户获取任务
:param t:
:return:
"""
startTime = datetime.now()
while True:
try:
# 从任务队列中获取任务数据
dict_json = self.redisUtils.getCon(SOURCE)
# print dict_json,'1234'
if dict_json is not None:
dict_json = decryptKwargs(dict_json)
name = dict_json.get('keyword','')
# 将token放入到thread中
logger.info("获取到任务,%s" % name)
# sendMail(u"邮件log测试",'*****@*****.**')
dict_json.update({"result": []})
self.taskWork(dict_json)
else:
finishTime = datetime.now()
if abs(finishTime.minute - startTime.minute) >= WAITTING:
break
time.sleep(1)
except Exception:
s = traceback.format_exc()
logger.error(s)
@Time()
def taskWork(self, dict_json):
"""
具体任务的工作方法,主要调用爬虫完成数据爬取
:param dict_json:
:return:
"""
token = dict_json['token']
try:
client = SpiderMain(dict_json)
logger.info("不需要抓取图片验证码,token:%s" % token)
p1 = threading.Thread(target=client.crawl, args=("user",))
# p2 = threading.Thread(target=client.crawl, args=("auto",))
p1.start()
# p2.start()
except Exception:
s = traceback.format_exc()
logger.error(s)
class SpiderMain(hypc_translate):
logger = logging.getLogger()
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.title = user.get("title", "")
# print chardet.detect(self.title)
self.title = urllib.quote(self.title.encode('utf8'))
self.project_district = user.get("project_district")
self.project_developer_name_value = user.get("project", "")
self.date_filter_min = user.get("date_filter_min","")
self.date_filter_max = user.get("date_filter_max","")
# print self.title,self.project_developer_name_value,self.project_district,self.date_filter_max,self.date_filter_min
# self.title = urllib.quote(self.title.decode(sys.stdin.encoding).encode('utf-8'))
# self.project_district = urllib.quote(self.project_district.decode(sys.stdin.encoding).encode('utf8'))
# self.project_developer_name_value = urllib.quote(self.project_developer_name_value.decode(sys.stdin.encoding).encode('utf8'))
# self.date_filter_min = urllib.quote(self.date_filter_min.decode(sys.stdin.encoding).encode('utf8'))
# self.date_filter_max = urllib.quote(self.date_filter_max.decode(sys.stdin.encoding).encode('utf8'))
#
self.token = user.get("token", "")
self.userid = user.get("userid", "")
self.LoginUrl = "https://newhouse.cnnbfdc.com"
self.result = user.get("result", "")
self.GJJInfo = []
self.bild = []
# 加入当次代理
# self.proxy = self._proxy()
def ifNotEmptyGetIndex(self, somelist, index=0):
"""check to see it's not empty"""
if somelist:
return somelist[index]
else:
return ''
def _proxy(self):
proxy = self.session.get(self.PROXYADDR).content
return {"http": "http://" + proxy, "https": "http://" + proxy}
def _errhtmlRecord(self, content):
'''
错误页面保存
'''
self.logger.info("保存错页内容")
try:
filename = str(uuid.uuid1()) + ".html"
sampleDir = os.path.join(os.path.dirname(__file__), "errorHtml").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(str(content))
self.logger.debug("已保存错页内容到{0}".format(filename))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存错页出错")
self.logger.warn("{0}".format(s))
def _sampleRecord(self, filename, content):
'''
保存网页内容
'''
self.logger.info("保存网页内容")
try:
sampleDir = os.path.join(os.path.dirname(__file__), "sample/").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存网页内容到{0}".format(sampleDir))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存网页出错")
self.logger.warn("{0}".format(s))
def _fetchUrl(self, url, data=None, header=None, timeout=TIMEOUT, fileName=None, proxy=None):
'''
抓取方法
'''
self.logger.info("开始抓取 {0}".format(url))
if header:
headers = header
self.logger.debug("伪装头：{0}".format(headers))
else:
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0"}
self.logger.debug("伪装头：{0}".format(headers))
for ir in range(REQUEST_RETRY):
try:
self.logger.debug("第{0}次 抓取".format(ir))
if data:
if proxy:
content = self.session.post(url, data=data, headers=headers, timeout=timeout, allow_redirects=False, proxies=proxy)
self.logger.debug("POST url：{0}， data：{1}, proxy: {2}".format(url, data, proxy))
else:
content = self.session.post(url, data=data, headers=headers, timeout=timeout, allow_redirects=False)
self.logger.debug("POST url：{0}， data：{1}".format(url, data))
else:
if proxy:
content = self.session.get(url, headers=headers, timeout=timeout, allow_redirects=False, proxies=proxy)
self.logger.debug("POST url：{0}, proxy: {1}".format(url, proxy))
else:
content = self.session.get(url, headers=headers, timeout=timeout, allow_redirects=False)
# print content.encoding
self.logger.debug("Get url：{0}".format(url))
if fileName and SAMPLEFLAG:
self._sampleRecord(fileName, content.content)
return content
except:
self.logger.error(traceback.format_exc())
self.logger.error("request url {0} failed ,check pls".format(url))
self.status = CRAWL_TIMEOUT
raise Exception("Failed to load url (%s)" % url)
def login(self,flag):
first_url = "https://newhouse.cnnbfdc.com/publicity/project-licenses?title="+str(self.title)+"&project_district="+str(self.project_district)+"&project_developer_name_value="+str(self.project_developer_name_value)+"&date_filter%5Bmin%5D%5Bdate%5D="+str(self.date_filter_min)+"&date_filter%5Bmax%5D%5Bdate%5D="+str(self.date_filter_min)
content = self._fetchUrl(url=first_url, header=LOGINHEADERS, fileName="login.html")
return str(content.text)
@Time()
def crawl(self, flag=""):
CurTime = datetime.now().strftime("%Y-%m-%d")
PastTime = (datetime.now() - timedelta(days=729)).strftime("%Y-%m-%d")
try:
# login
content = self.login(flag)
url_num = re.compile(r'/project_license_view/([0-9]+)">')
url_num_list = url_num.findall(content)
if len(url_num_list) > 0:
for url_num in url_num_list:
url_detail = self.LoginUrl + '/project_license_view/' + str(url_num)
self.logger.info("可查询到您查的信息：%s" % self.title)
# 项目详情信息
content = self._fetchUrl(url=url_detail, header=PERHEADERS, fileName="person.html")
detail = etree.HTML(content.text)
project_name = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='project-detail__info']/div[1]/h1/text()")) # 项目名称
alias_name = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='project-detail__info']/div[1]/div/text()")) # 别名
positioning = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='project-detail__info']/div[2]//span/text()"))#定位
company_name = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='project-detail__info']/div[3]//span/text()")) # 公司名称
project_id = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='project-detail__info']/div[4]/span/text()")) #项目编号
counts = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-entity-view pane-node']/div[2]/div[2]/div/div[1]/div/text()")) or self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-entity-view pane-node']/div[2]/div/div[2]/div[1]/div/strong/text()")) # 套数
area = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-entity-view pane-node']/div[2]/div[2]/div/div[2]/div/text()")) or self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-entity-view pane-node']/div[2]/div/div[2]/div[2]/div/strong/text()"))# 面积
#数据汇总
marketable_area = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-first']/div/div[1]/div/text()"))# 可销售面积
sales_area = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-first']/div/div[2]/div/text()"))#已销售面积
has_sold_area = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-first']/div/div[3]/div/text()")) #已销售非住宅面积
number_sellable_households = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-last']/div/div[1]/div/text()")) # 可售户数
has_sold_number = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-last']/div/div[2]/div/text()")) # 已销售户数
has_sold_households = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-panel panel-col-last']/div/div[3]/div/text()")) # 已销售非住宅户数
# 详细参数
permit_number = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[1]/td[2]/text()"))# 许可证号
permission_date = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[1]/td[4]/span/text()"))# 许可日期
sales_address = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[2]/td[2]/text()"))# 售楼地址
sales_call = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[2]/td[4]/text()"))# 售楼电话
number_buildings = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[3]/td[2]/text()"))# 幢数
construction_area = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[3]/td[4]/text()"))# 建筑面积
opening_time = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[4]/td[2]/span/text()"))# 开盘时间
supervision_account = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[4]/td[4]/text()"))# 资金监管账户
document_authority = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[5]/td[2]/text()"))# 证件发布机构
financial_bank = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='parameter-table']/tr[5]/td[4]/text()"))# 资金监管银行
# 楼栋信息
loudong_list = detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div")
if len(loudong_list) > 0:
for i in range(len(loudong_list)):
i = i + 1
num_floors = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[1]/div/text()")) # 楼号
total_floors = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[2]/div/text()")) # 总层数
# total_houses = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[3]/div/text()")) # 总户数
total_houses = ''
permitted_households = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[3]/div/text()")) # 许可户数
has_sold_number_households = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[4]/div/text()")) # 已销售户数
has_sold_residential_households = self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[5]/div/text()")) # 已销售非住宅户数
wangqian_list = []
wangqian = str(self.ifNotEmptyGetIndex(detail.xpath("//*[@class='panel-pane pane-views-panes pane-project-license-buildings-panel-pane-1']/div/div/div["+str(i)+"]/div[6]/span/a/@href"))) # 网签的URL
if wangqian:
lou_numb = re.compile(r'buildingId=([0-9]+)')
wang_numb = self.ifNotEmptyGetIndex(lou_numb.findall(wangqian))
wangqian_url = "https://newhouse.cnnbfdc.com//map-api-v1/building_units?args[]=" + wang_numb
wang_content = self._fetchUrl(url=wangqian_url, header=IMGHEADERS, fileName="wangqian.html")
wangqian_info = etree.HTML(str(wang_content.text))
for j in range(len(wangqian_info.xpath("//result/item"))):
j = j + 1
if self.ifNotEmptyGetIndex(wangqian_info.xpath("//result/item["+str(j)+"]/state/text()")) == '3':
number = self.ifNotEmptyGetIndex(wangqian_info.xpath("//result/item["+str(j)+"]/number/text()"))
wangqian_list.append(number)
self.bild.append(hypc_translate.detail_building(
num_floors = num_floors,
total_floors = total_floors,
total_houses = total_houses,
permitted_households = permitted_households,
has_sold_number_households = has_sold_number_households,
has_sold_residential_households = has_sold_residential_households,
wangqian_nubm=wangqian_list
))
else:
self.bild.append(hypc_translate.detail_building(
num_floors = '',
total_floors = '',
total_houses = '',
permitted_households = '',
has_sold_number_households = '',
has_sold_residential_households = '',
))
self.GJJInfo.append(hypc_translate.baseinfo(
project_name = project_name,
alias_name = alias_name, # 别名
positioning = positioning, #定位
company_name = company_name, # 公司名称
project_id = project_id, #项目编号
counts = counts, # 套数
area = area, # 面积
marketable_area = marketable_area, # 可销售面积
sales_area = sales_area, #已销售面积
has_sold_area = has_sold_area, #已销售非住宅面积
number_sellable_households = number_sellable_households, # 可售户数
has_sold_number = has_sold_number, # 已销售户数
has_sold_households = has_sold_households, # 已销售非住宅户数
permit_number = permit_number, # 许可证号
permission_date = permission_date, # 许可日期
sales_address = sales_address, # 售楼地址
sales_call = sales_call, # 售楼电话
number_buildings = number_buildings, # 幢数
construction_area = construction_area, # 建筑面积
opening_time = opening_time, # 开盘时间
supervision_account = supervision_account, # 资金监管账户
document_authority = document_authority, # 证件发布机构
financial_bank = financial_bank, # 资金监管银行
bulding = self.bild
))
self.logger.info("解析完成")
self.status= CRAWL_SUCCESS
self.result.append(self.GJJInfo)
else:
self.logger.info("暂无您查询的信息：%s" % IDCARD_ERROR_DESC)
self.status= CRAWL_SUCCESS
self.result.append(self.GJJInfo)
except:
s = traceback.format_exc()
self.logger.error("抓取错误：%s" % s)
self.status, self.desc = CRAWL_FAIL, PROGRAM_ERROR_DESC
finally:
try:
if len(self.result) == 1 and self.status == CRAWL_SUCCESS:
self.desc = CRAWL_SUCCESS_DESC
# print self.result
result_json = json.dumps(self.result[0], ensure_ascii=False)
# print result_json
self.redisUtils.setNotify(type=TYPEVALUE,token=self.token, val="1", decs="抓取成功！", result=result_json)
# self.push_data(TYPEVALUE, self.userid, result_json)
elif self.status == CRAWL_FAIL:
self.desc = CRAWL_FAIL_DESC
elif self.status == CRAWL_TIMEOUT:
self.desc = CRAWL_TIMEOUT_DESC
elif self.status == IDCARD_ERROR:
self.desc = IDCARD_ERROR_DESC
elif self.status == PASSWORD_ERROR:
self.desc = PASSWORD_ERROR_DESC
elif self.status == BCODE_ERROR:
self.desc = BCODE_ERROR_DESC
else:
self.desc = PROGRAM_ERROR_DESC
except Exception as e:
s = traceback.format_exc()
self.logger.error(s)
finally:
try:
self.redisUtils.setNotify(type=TYPEVALUE, token=self.token, val=self.status, decs=self.desc)
except Exception:
s = traceback.format_exc()
self.logger.error(s)
def zipToStr(self, content):
'''
使用urllib2获取到的内容被压缩，需要进行解压缩
:param content: 需要解压的内容
:return:
'''
try:
conn = zlib.decompress(content, 16 + zlib.MAX_WBITS)
return conn
except:
self.logger.error('解压缩响应内容出错%s' % traceback.format_exc())
raise Exception("解压缩响应内容出错%s" % traceback.format_exc())
class CrawlBase(object):
def __init__(self, dict_json, key=[], verifycode_type='png'):
self.redisUtils = RedisUtils()
self.damatuWeb = damatuWeb
self.PROXYADDR = PROXYADDR
self.dict_json = dict_json
self.token = self.dict_json['token']
self.verifycode_type = verifycode_type
self.status = None
self.desc = None
self.current_milli_time = lambda: str(int(round(time.time() * 1000)))
self.startTime = self.current_milli_time()
self.realpath = os.path.split(os.path.realpath(__file__))[0]
filename = 'verifycode/%s_verifycode.%s' % (self.startTime,
verifycode_type)
self.code_path = os.path.join(self.realpath, filename)
logging.config.fileConfig('unicom/logging.config')
self.logger = logging.getLogger('flow')
# 是否保存用户目录，默认为爬虫出错才保存，也可以手动修改
self.rmuserdirFlag = False
self.mkUserdir(key)
''' 用户信息以及爬取页面记录，爬取成功会删除，失败则会保存下来便于排错 '''
def mkUserdir(self, key=[]):
# 创建用户文件夹
fn = os.path.join(self.realpath, 'sample',
'%s_%s' % (self.startTime, self.dict_json['token']))
os.mkdir(fn)
# 覆盖敏感信息
info_dict = copy.deepcopy(self.dict_json)
for k in key:
info_dict[k] = u'******'
with open(os.path.join(fn, 'dict_json.txt'), 'w') as f:
f.write(str(info_dict))
self.userdir = fn
return
def rmUserdir(self, fn):
shutil.rmtree(fn)
def takePage(self, n, content, msg=None):
fn = os.path.join(self.userdir, n)
with open(fn, 'w') as f:
f.write(content)
if msg:
with open(fn, 'a') as f:
f.write('\n' * 5 + '#' * 60 + '\n' * 3 + msg)
''' 验证码交互相关 '''
def get_verifycode(self, codeUrl=None):
# 获取图片验证码，并发送通知，如果是短信验证码，或者必须使用driver，可重写此函数
if callable(codeUrl):
codeUrl = codeUrl()
codeContent = self.session.get(codeUrl).content
bcode = base64.b64encode(codeContent)
self.redisUtils.setNotify(token=self.token,
val=NEED_MORE,
decs='需要图片验证码',
result='data:image/jpg;base64,' + bcode)
self.logger.info('验证码已发送')
def judge_verifycode(self, inputValue, ResetCode):
# verifycode_handler会根据此函数的返回值判断验证码对错
# 判断验证码对错，爬虫自定义，如果验证码不是错误的，此函数的返回值，将被verifycode_handler()返回
pass
def get_input(self):
# 获取用户输入
stime = datetime.now()
self.logger.info('等待用户输入')
while True:
inputValue = self.redisUtils.getNotify(self.token, 'bcode')
if inputValue:
return inputValue
else:
eclipseTimes = datetime.now() - stime
if eclipseTimes.total_seconds() > WAITTIME:
self.logger.info('接收用输入超时:%s' % self.token)
self.status = INPUT_ERROR
self.desc = '接收用输入超时'
time.sleep(1)
return
def verifycode_handler(self, codeUrl=None, ResetCode=False):
# 交互流程，接受用户响应，可以选择刷新验证码，或者输入验证码
# ResetCode 可控制是否保持会话，开启验证码刷新功能，默认不保持会话
self.logger.info('需要验证码')
self.get_verifycode(codeUrl)
while True:
inputValue = self.get_input()
if inputValue == 'reset':
if ResetCode:
self.logger.info('用户刷新验证码')
self.redisUtils.DelNotify(self.token, 'bcode')
self.get_verifycode(codeUrl)
continue
elif inputValue == None:
return
else:
# 验证码输入是否正确
result = self.judge_verifycode(inputValue, ResetCode)
if result:
return result
else:
if ResetCode:
self.redisUtils.DelNotify(self.token, 'bcode')
self.redisUtils.setNotify(token=self.token,
val=INPUT_ERROR,
decs='验证码错误')
self.logger.info('验证码错误')
continue
self.status = INPUT_ERROR
self.desc = '验证码错误'
return
class SpiderMain(craw_dishonest):
logger = logging.getLogger()
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.username = urllib.quote(user.get("name", ""))
self.idcard = urllib.quote(user.get("idcard", ""))
self.area = urllib.quote(user.get("area", ""))
self.token = user.get("token", "")
self.userid = user.get("userid", "")
# urllib.quote(a)
self.LoginUrl = "https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?" + "resource_id=6899&query=%E5%A4%B1%E4%BF%A1%E8%A2%AB%E6%89%A7%E8%A1%8C%E4%BA%BA%E5%90%8D%E5%8D%95&cardNum=" + self.idcard + "&iname=" + self.username + "&areaName=" + self.area + "&ie=utf-8&oe=utf-8&format=json&t=" + str(
int(round(time.time() *
1000))) + "&cb=jQuery110207690611877233657_" + str(
int(round(time.time() * 1000))) + "&_=" + str(
int(round(time.time() * 1000)))
self.result = user.get("result", "")
self.GJJInfo = []
self.PerInfo = {}
self.PayRecord = {}
# 加入当次代理
# self.proxy = self._proxy()
def _proxy(self):
proxy = self.session.get(self.PROXYADDR).content
return {"http": "http://" + proxy, "https": "http://" + proxy}
def _errhtmlRecord(self, content):
'''
错误页面保存
'''
self.logger.info("保存错页内容")
try:
filename = str(uuid.uuid1()) + ".html"
sampleDir = os.path.join(os.path.dirname(__file__),
"errorHtml").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存错页内容到{0}".format(filename))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存错页出错")
self.logger.warn("{0}".format(s))
def _sampleRecord(self, filename, content):
'''
保存网页内容
'''
self.logger.info("保存网页内容")
try:
sampleDir = os.path.join(os.path.dirname(__file__),
"sample/").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存网页内容到{0}".format(sampleDir))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存网页出错")
self.logger.warn("{0}".format(s))
def _fetchUrl(self,
url,
data=None,
header=None,
timeout=TIMEOUT,
fileName=None,
proxy=None):
'''
抓取方法
'''
self.logger.info("开始抓取 {0}".format(url))
if header:
headers = header
self.logger.debug("伪装头：{0}".format(headers))
else:
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0"
}
self.logger.debug("伪装头：{0}".format(headers))
for ir in range(REQUEST_RETRY):
try:
self.logger.debug("第{0}次 抓取".format(ir))
if data:
if proxy:
content = self.session.post(url,
data=data,
headers=headers,
timeout=timeout,
allow_redirects=False,
proxies=proxy)
self.logger.debug(
"POST url：{0}， data：{1}, proxy: {2}".format(
url, data, proxy))
else:
content = self.session.post(url,
data=data,
headers=headers,
timeout=timeout,
allow_redirects=False)
self.logger.debug("POST url：{0}， data：{1}".format(
url, data))
else:
if proxy:
content = self.session.get(url,
headers=headers,
timeout=timeout,
allow_redirects=False,
proxies=proxy)
self.logger.debug("Get url：{0}, proxy: {1}".format(
url, proxy))
else:
content = self.session.get(url,
headers=headers,
timeout=timeout,
allow_redirects=False)
self.logger.debug("Get url：{0}".format(url))
if fileName and SAMPLEFLAG:
self._sampleRecord(fileName, content.content)
return content
except:
self.logger.error(traceback.format_exc())
self.logger.error("request url {0} failed ,check pls".format(url))
self.status = CRAWL_TIMEOUT
raise Exception("Failed to load url (%s)" % url)
def _save_captcha(self):
"""
下载验证码，返回图片b64编码，
"""
self.logger.info("刷新验证码")
try:
codeContent = self.session.get(self.codeUrl,
headers=IMGHEADERS).content
self.logger.debug("验证码二进制内容：{0}".format(codeContent)[:50])
self.logger.info("下载验证码")
self.status = NEED_BCODE
with open(
os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/"), 'wb') as f:
f.write(codeContent)
self.logger.info("验证码图片已保存!")
bcode = base64.b64encode(codeContent)
# self.logger.debug("{}".format(bcode))
return bcode
except:
s = traceback.format_exc()
self.logger.error("刷新验证码错误：%s" % s)
return PROGRAM_ERROR, {"error": "超时或代码异常"}
def _captcha_recognize(self, imgpath):
'''
自动识别验证码
:param fileName:
:return:
'''
img = Image.open(imgpath)
for i in range(10):
code = image_to_string(img, lang='eng').encode('utf-8')
if code.isalnum() and len(code) == 4:
self.logger.info(code)
return code
self._save_captcha()
time.sleep(0.05)
def _ChioceIdent(self, flag):
'''
选择识别方式
:param flag:
:return:
'''
if flag == 'dmt':
self._save_captcha()
self.startTime = str(datetime.now())
dmt = damatuWeb.DamatuApi("huoyan2016", "123456")
# self.imageCode = dmt.decodeUrl(self.captchaId_url, 200)
self.imageCode = dmt.decode(
os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/"), 200)
self.finishTime = str(datetime.now())
elif flag == 'input':
self._save_captcha()
pngPath = os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/")
self.logger.info("验证码路径：{0}".format(pngPath))
self.imageCode = raw_input("请输入验证码:")
elif flag == 'auto':
self.startTime = str(datetime.now())
self._save_captcha()
self.logger.info("识别验证码")
pngPath = os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/")
self.imageCode = self._captcha_recognize(pngPath)
self.logger.debug("验证码内容：{0}".format(self.imageCode))
self.finishTime = str(datetime.now())
# 返回给用户 通知redis 返回base64
elif flag == 'user':
self.startTime = datetime.now()
bcode64 = self._save_captcha()
self.redisUtils.setNotify(token=self.token,
val="10",
decs="需要图片验证码",
result="data:image/jpg;base64," +
bcode64)
# 向session中放入数据
while True:
# 等待获取用户输入要的图片验证码值
dict_image_code = self.redisUtils.getNotify(
self.token, "bcode")
if dict_image_code is not None:
self.imageCode = dict_image_code
return
else:
self.finishTime = datetime.now()
if abs(self.finishTime.minute -
self.startTime.minute) >= 3:
break
# 爬虫等待用户输入图片验证码超时
self.logger.warn("爬虫等待用户输入图片验证码超时:%s" % self.token)
time.sleep(1)
else:
self.status = NOT_NEED_BCODE
self.logger.info(NOT_NEED_BCODE_DESC)
def login(self, flag):
# self._ChioceIdent(flag)
if self.username or self.idcard:
content = self._fetchUrl(url=self.LoginUrl,
header=LOGINHEADERS,
fileName="login.html")
return content
else:
return ''
@Time()
def crawl(self, flag=""):
CurTime = datetime.now().strftime("%Y-%m-%d")
PastTime = (datetime.now() - timedelta(days=729)).strftime("%Y-%m-%d")
try:
# login
# for i in range(10):
content = self.login(flag)
if content:
info_re = re.compile(r'\/\*\*\/jQuery[0-9]+_[0-9]+\((.*)\)')
info_detail = ifNotEmptyGetIndex(
info_re.findall(content.content))
info_dict = eval(info_detail)
date_info = ifNotEmptyGetIndex(info_dict.get('data', ''))
if not date_info:
date_info = {'result': ''}
info_result = date_info.get('result', '')
for detail in info_result:
re_id = re.compile(r'id=([0-9]*)')
shixinid = ifNotEmptyGetIndex(
re_id.findall(detail.get("loc", "")))
self.GJJInfo.append(
craw_dishonest.gaofa(
unperformPart=detail.get("unperformPart",
""), # 被执行人的未履行部分
shixinid=shixinid, # 失信人ID
sexy=detail.get("sexy", ""), # 性别
regDate=detail.get("regDate", ""), # 立案时间
publishDate=detail.get("publishDate", ""), # 发布时间
performedPart=detail.get("performedPart",
""), # 被执行人的履行部分
performance=detail.get("performance",
""), # 被执行人的履行情况
partyTypeName=detail.get("partyTypeName",
""), # 类型号
iname=detail.get("iname", ""), # 被执行人姓名/名称
disruptTypeName=detail.get("disruptTypeName",
""), # 失信被执行人行为具体情形
courtName=detail.get("courtName", ""), # 执行法院
caseCode=detail.get("caseCode", ""), # 案号
cardNum=detail.get("cardNum", ""), # 身份证号码/组织机构代码
businessEntity=detail.get("businessEntity",
""), # 法定代表人或负责人姓名
areaName=detail.get("areaName", ""), # 省份
age=detail.get("age", ""), # 年龄（企业默认为0）
duty=detail.get("duty", ""), # 生效法律文书确定的义务
gistId=detail.get("gistId", ""), # 执行依据文号
gistUnit=detail.get("gistUnit", ""), # 做出执行依据单位
))
self.status = CRAWL_SUCCESS
self.result.append(self.GJJInfo)
else:
self.status = CRAWL_SUCCESS
self.result.append(self.GJJInfo)
except:
s = traceback.format_exc()
self.logger.error("抓取错误：%s" % s)
self.status, self.desc = EXEMPLE_IS_NOT_FULL, EXEMPLE_IS_NOT_FULL_DESC
finally:
try:
if len(self.result) == 1 and self.status == CRAWL_SUCCESS:
self.desc = CRAWL_SUCCESS_DESC
# print self.result
result_json = json.dumps(self.result[0],
ensure_ascii=False)
# print result_json
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val="1",
decs="抓取成功！",
result=result_json)
# self.push_data(TYPEVALUE, self.userid, result_json)
elif self.status == CRAWL_FAIL:
self.desc = CRAWL_FAIL_DESC
elif self.status == CRAWL_TIMEOUT:
self.desc = CRAWL_TIMEOUT_DESC
elif self.status == IDCARD_ERROR:
self.desc = IDCARD_ERROR_DESC
elif self.status == PASSWORD_ERROR:
self.desc = PASSWORD_ERROR_DESC
elif self.status == BCODE_ERROR:
self.desc = BCODE_ERROR_DESC
else:
self.desc = PROGRAM_ERROR_DESC
except Exception as e:
s = traceback.format_exc()
self.logger.error(s)
finally:
try:
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val=self.status,
decs=self.desc)
except Exception:
s = traceback.format_exc()
self.logger.error(s)
def zipToStr(self, content):
'''
使用urllib2获取到的内容被压缩，需要进行解压缩
:param content: 需要解压的内容
:return:
'''
try:
conn = zlib.decompress(content, 16 + zlib.MAX_WBITS)
return conn
except:
self.logger.error('解压缩响应内容出错%s' % traceback.format_exc())
raise Exception("解压缩响应内容出错%s" % traceback.format_exc())
class SpiderMain(craw_taxpayer_qualification):
logger = logging.getLogger()
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.fpjy = user.get("fpjy", "")
self.fpdm = user.get("fpdm", "")
self.fphm = user.get("fphm", "")
self.kprq = user.get("kprq", "")
self.fpje = user.get("fpje", "")
self.token = user.get("token", "")
self.userid = user.get("userid", "")
self.fpdm_area = self.fpdm[0:4]
self.fpdm_url = AREA.get(self.fpdm_area, "")
self.suiji = str(int(round(time.time() * 1000)))
self.codeUrl = self.fpdm_url + '/WebQuery/yzmQuery?callback=jQuery110204713398352365614_' + self.suiji + '&fpdm=' + self.fpdm + '&r=' + str(
'%.16f' %
(random.random())) + '&v=V1.0.04_001' + '&nowtime=' + str(
int(round(time.time() * 1000))
) + '&publickey=B8EE27C2CFEABABBD1DB92F4D84E4EA3&_=' + str(
int(round(time.time() * 1000)))
self.result = user.get("result", "")
self.GJJInfo = []
self.PerInfo = {}
# 加入当次代理
# self.proxy = self._proxy()
def _proxy(self):
proxy = self.session.get(self.PROXYADDR).content
return {"http": "http://" + proxy, "https": "http://" + proxy}
def _errhtmlRecord(self, content):
'''
错误页面保存
'''
self.logger.info("保存错页内容")
try:
filename = str(uuid.uuid1()) + ".html"
sampleDir = os.path.join(os.path.dirname(__file__),
"errorHtml").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存错页内容到{0}".format(filename))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存错页出错")
self.logger.warn("{0}".format(s))
def _sampleRecord(self, filename, content):
'''
保存网页内容
'''
self.logger.info("保存网页内容")
try:
sampleDir = os.path.join(os.path.dirname(__file__),
"sample/").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存网页内容到{0}".format(sampleDir))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存网页出错")
self.logger.warn("{0}".format(s))
def _fetchUrl(self,
url,
data=None,
header=None,
timeout=TIMEOUT,
fileName=None,
proxy=None):
'''
抓取方法
'''
self.logger.info("开始抓取 {0}".format(url))
if header:
headers = header
self.logger.debug("伪装头：{0}".format(headers))
else:
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0"
}
self.logger.debug("伪装头：{0}".format(headers))
for ir in range(REQUEST_RETRY):
try:
self.logger.debug("第{0}次 抓取".format(ir))
if data:
if proxy:
content = self.session.post(url,
data=data,
headers=headers,
timeout=timeout,
allow_redirects=False,
proxies=proxy)
self.logger.debug(
"POST url：{0}， data：{1}, proxy: {2}".format(
url, data, proxy))
else:
content = self.session.post(url,
data=data,
headers=headers,
timeout=timeout,
allow_redirects=False)
self.logger.debug("POST url：{0}， data：{1}".format(
url, data))
else:
if proxy:
content = self.session.get(url,
headers=headers,
timeout=timeout,
allow_redirects=False,
proxies=proxy)
self.logger.debug("POST url：{0}, proxy: {1}".format(
url, proxy))
else:
content = self.session.get(url,
data=data,
headers=headers,
timeout=timeout,
allow_redirects=False)
self.logger.debug("Get url：{0}".format(url))
if fileName and SAMPLEFLAG:
self._sampleRecord(fileName, content.content)
info = re.compile(r'jQuery[0-9]+_[0-9]+\((.*)\)')
info_list = info.findall(content.content)[0]
content_dic = eval(info_list)
return content_dic
except:
self.logger.error(traceback.format_exc())
self.logger.error("request url {0} failed ,check pls".format(url))
self.status = CRAWL_TIMEOUT
raise Exception("Failed to load url (%s)" % url)
def _save_captcha(self):
"""
下载验证码，返回图片b64编码，
"""
self.logger.info("刷新验证码")
try:
content = self.session.get(self.codeUrl,
headers=IMGHEADERS,
verify=False)
info = re.compile(r'jQuery[0-9]+_[0-9]+\((.*)\)')
info_list = ifNotEmptyGetIndex(info.findall(content.content))
dic = eval(info_list)
codeContent = dic.get('key1', '')
self.logger.debug("验证码二进制内容：{0}".format(codeContent)[:50])
self.logger.info("下载验证码")
self.status = NEED_BCODE
chose_id = dic.get('key4', '')
chose_info = COULOR.get(chose_id, '')
codeContent1 = base64.b64decode(codeContent)
with open(
os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/"), 'wb') as f:
f.write(codeContent1)
bcode = codeContent
self.logger.info("验证码图片已保存!")
if chose_info != '请输入验证码内容':
im = Image.open(
os.path.join(os.path.dirname(__file__), "captcha.png"))
box = im.copy()
u = Image.new('RGB', (90, 55))
u.paste(box, (0, 0))
key_id = Image.open(
os.path.join(os.path.dirname(__file__), chose_info))
key_box = key_id.copy()
u.paste(key_box, (0, 35))
u.save(os.path.join(os.path.dirname(__file__), "card.png"))
with open(os.path.join(os.path.dirname(__file__),
"card.png")) as c:
bcode = base64.b64encode(c.read())
self.data = urllib.quote(dic.get('key2',
'').encode('utf8')).replace(
'%20', '+')
self.index = dic.get('key3', '')
return bcode
except:
s = traceback.format_exc()
self.logger.error("刷新验证码错误：%s" % s)
return PROGRAM_ERROR, {"error": "超时或代码异常"}
def _captcha_recognize(self, imgpath):
'''
自动识别验证码
:param fileName:
:return:
'''
img = Image.open(imgpath)
for i in range(10):
code = image_to_string(img, lang='eng').encode('utf-8')
if code.isalnum() and len(code) == 4:
self.logger.info(code)
return code
self._save_captcha()
time.sleep(0.05)
def _ChioceIdent(self, flag):
'''
选择识别方式
:param flag:
:return:
'''
if flag == 'dmt':
self._save_captcha()
self.startTime = str(datetime.now())
dmt = damatuWeb.DamatuApi("huoyan2016", "123456")
self.imageCode = dmt.decode(
os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/"), 200)
self.finishTime = str(datetime.now())
elif flag == 'input':
self._save_captcha()
pngPath = os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/")
self.logger.info("验证码路径：{0}".format(pngPath))
self.imageCode = raw_input("请输入验证码:")
elif flag == 'auto':
self.startTime = str(datetime.now())
self._save_captcha()
self.logger.info("识别验证码")
pngPath = os.path.join(os.path.dirname(__file__),
"captcha.png").replace("\\", "/")
self.imageCode = self._captcha_recognize(pngPath)
self.logger.debug("验证码内容：{0}".format(self.imageCode))
self.finishTime = str(datetime.now())
# 返回给用户 通知redis 返回base64
elif flag == 'user':
self.startTime = datetime.now()
bcode64 = self._save_captcha()
self.redisUtils.setNotify(token=self.token,
val="10",
decs="需要图片验证码",
result="data:image/jpg;base64," +
bcode64)
# 向session中放入数据
while True:
# 等待获取用户输入要的图片验证码值
dict_image_code = self.redisUtils.getNotify(
self.token, "bcode")
# print dict_image_code
if dict_image_code is not None:
# print dict_image_code
self.redisUtils.DelNotify(self.token, "bcode")
self.imageCode = dict_image_code
break
else:
self.finishTime = datetime.now()
if abs(self.finishTime.minute -
self.startTime.minute) >= 2:
break
time.sleep(1)
else:
self.status = NOT_NEED_BCODE
self.logger.info(NOT_NEED_BCODE_DESC)
def login(self, flag):
self._ChioceIdent(flag)
if self.fpje:
# LoginUrl = self.fpdm_url+'/WebQuery/query?callback=jQuery110204713398352365614_'+self.suiji+'&fpdm='+self.fpdm+'&fphm='+self.fphm+'&kprq='+self.kprq+'&fpje='+self.fpje+'&fplx=01&yzm='+self.imageCode+'&yzmSj='+self.data+'&index='+self.index+'&iv=31205b0a9543d0cf808f6a3a19915858'+'&salt=bc1792b6b19a7ceb8f124fc75e658cfe'+'&publickey=89FF3E78F5B40654133317B104D81634&_='+str(int(round(time.time() * 1000)))
LoginUrl = self.fpdm_url + '/WebQuery/invQuery?callback=jQuery110204713398352365614_' + self.suiji + '&fpdm=' + self.fpdm + '&fphm=' + self.fphm + '&kprq=' + self.kprq + '&fpje=' + self.fpje + '&fplx=01&yzm=' + self.imageCode + '&yzmSj=' + self.data + '&index=' + self.index + '&iv=31205b0a9543d0cf808f6a3a19915858' + '&salt=bc1792b6b19a7ceb8f124fc75e658cfe' + '&publickey=89FF3E78F5B40654133317B104D81634&_=' + str(
int(round(time.time() * 1000)))
content = self._fetchUrl(url=LoginUrl,
header=IMGHEADERS,
fileName="login.html")
elif self.fpjy:
LoginUrl = self.fpdm_url + '/WebQuery/invQuery?callback=jQuery110204713398352365614_' + self.suiji + '&fpdm=' + self.fpdm + '&fphm=' + self.fphm + '&kprq=' + self.kprq + '&fpje=' + self.fpjy + '&fplx=04&yzm=' + self.imageCode + '&yzmSj=' + self.data + '&index=' + self.index + '&iv=31205b0a9543d0cf808f6a3a19915858' + '&salt=bc1792b6b19a7ceb8f124fc75e658cfe' + '&publickey=89FF3E78F5B40654133317B104D81634&_=' + str(
int(round(time.time() * 1000)))
content = self._fetchUrl(url=LoginUrl,
header=IMGHEADERS,
fileName="login.html")
else:
self.logger.debug("没有您查询的方式")
content = {"key1": "009"}
return content
@Time()
def crawl(self, flag=""):
CurTime = datetime.now().strftime("%Y-%m-%d")
PastTime = (datetime.now() - timedelta(days=729)).strftime("%Y-%m-%d")
try:
# login
for i in range(5):
content = self.login(flag)
if content['key1'] == "007":
self.logger.info("验证码失效")
self.status, self.desc = BCODE_ERROR, CARD_OUT_DESC
continue
elif content['key1'] == "008":
self.logger.info("验证码错误")
self.status, self.desc = BCODE_ERROR, BCODE_ERROR_DESC
continue
elif content["key1"] == "002":
self.logger.info("当日查询次数已超过5次")
self.logger.info(PASSWORD_ERROR_DESC)
self.status, self.desc = PASSWORD_ERROR, PASSWORD_ERROR_DESC
break
elif content['key1'] == "009":
self.logger.info("查无此票")
self.logger.info(EXEMPLE_IS_NOT_FULL)
self.status, self.desc = EXEMPLE_IS_NOT_FULL, EXEMPLE_IS_NOT_FULL_DESC
break
elif content["key1"] == "001":
self.logger.info("登陆成功：%s" % content['key1'])
a_json = json.dumps(content, ensure_ascii=False)
bbb = json.loads(a_json, encoding="gbk")
sales_name = bbb.get(
'key2', '').encode('utf8').split('≡')[6] # 销售方名字【6】
purchaser_taxpayer_id = bbb.get(
'key2',
'').encode('utf8').split('≡')[3] # 购买方纳税人识别号【3】
purchaser_bank_account = bbb.get(
'key2',
'').encode('utf8').split('≡')[5] # 购买方开户行级账号【5】
sales_taxpayer_id = bbb.get(
'key2', '').encode('utf8').split('≡')[7] # 销售方纳税识别号【7】
sales_add_phone = bbb.get(
'key2', '').encode('utf8').split('≡')[8] # 销售方地址电话【8】
check_number = bbb.get(
'key2', '').encode('utf8').split('≡')[17] # 校验号
sales_bank_account = bbb.get(
'key2',
'').encode('utf8').split('≡')[9] # 销售方开户行及账号【9】
purchaser_add_phone = bbb.get(
'key2', '').encode('utf8').split('≡')[4] # 购买方地址电话[4]
purchaser_name = bbb.get(
'key2', '').encode('utf8').split('≡')[2] # 购买方名称[2]
service_name = bbb.get(
'key3', '').encode('utf8').split('█')[0] # 服务名称
specification = bbb.get(
'key3', '').encode('utf8').split('█')[1] # 规格型号
unit = bbb.get('key3',
'').encode('utf8').split('█')[2] # 单位
quantity = bbb.get('key3',
'').encode('utf8').split('█')[3] # 数量
unit_price = bbb.get('key3',
'').encode('utf8').split('█')[4] # 单价
amount = bbb.get('key3',
'').encode('utf8').split('█')[5] # 金额
tax_rate = bbb.get('key3',
'').encode('utf8').split('█')[6] # 税率
tax = bbb.get('key3',
'').encode('utf8').split('█')[7] # 税额
if self.fpjy:
machine_code = bbb.get(
'key2', '').encode('utf8').split('≡')[15] #机器码
else:
machine_code = ''
self.PerInfo = craw_taxpayer_qualification.baseinfo(
sales_name=sales_name,
purchaser_taxpayer_id=purchaser_taxpayer_id,
purchaser_bank_account=purchaser_bank_account,
sales_taxpayer_id=sales_taxpayer_id,
sales_add_phone=sales_add_phone,
sales_bank_account=sales_bank_account,
purchaser_add_phone=purchaser_add_phone,
purchaser_name=purchaser_name,
service_name=service_name,
specification=specification,
unit=unit,
quantity=quantity,
unit_price=unit_price,
amount=amount,
tax_rate=tax_rate,
tax=tax,
invoice_code=self.fpdm, # 发票代码
invoice_number=self.fphm, # 发票号码
billing_date=self.kprq, # 开票日期
check_number=check_number, # 校验号
machine_code=machine_code, # 机器码
before_tax=self.fpje, #税前金额
total_tax='%.2f' %
(float(amount) + float(tax)), # 纳税合计
)
self.GJJInfo.append(self.PerInfo)
self.status = CRAWL_SUCCESS
self.result.append(self.GJJInfo)
break
else:
self.logger.info("查询失败：%s" % content["key1"])
self.logger.info(IDCARD_ERROR_DESC)
self.status, self.desc = IDCARD_ERROR, IDCARD_ERROR_DESC
break
except:
s = traceback.format_exc()
self.logger.error("抓取错误：%s" % s)
self.status, self.desc = self.status, PROGRAM_ERROR_DESC
finally:
try:
if len(self.result) == 1 and self.status == CRAWL_SUCCESS:
self.desc = CRAWL_SUCCESS_DESC
# print self.result
result_json = json.dumps(self.result[0],
ensure_ascii=False)
# print result_json
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val="1",
decs="抓取成功！",
result=result_json)
# self.push_data(TYPEVALUE, self.userid, result_json)
elif self.status == CRAWL_FAIL:
self.desc = CRAWL_FAIL_DESC
elif self.status == CRAWL_TIMEOUT:
self.desc = CRAWL_TIMEOUT_DESC
elif self.status == IDCARD_ERROR:
self.desc = IDCARD_ERROR_DESC
elif self.status == PASSWORD_ERROR:
self.desc = PASSWORD_ERROR_DESC
elif self.status == BCODE_ERROR:
self.desc = BCODE_ERROR_DESC
else:
self.desc = PROGRAM_ERROR_DESC
except Exception as e:
s = traceback.format_exc()
self.logger.error(s)
finally:
try:
self.redisUtils.setNotify(type=TYPEVALUE,
token=self.token,
val=self.status,
decs=self.desc)
except Exception:
s = traceback.format_exc()
self.logger.error(s)
def zipToStr(self, content):
'''
使用urllib2获取到的内容被压缩，需要进行解压缩
:param content: 需要解压的内容
:return:
'''
try:
conn = zlib.decompress(content, 16 + zlib.MAX_WBITS)
return conn
except:
self.logger.error('解压缩响应内容出错%s' % traceback.format_exc())
raise Exception("解压缩响应内容出错%s" % traceback.format_exc())
class SpiderMain(hypc_soufun):
logger = logging.getLogger()
def __init__(self, user):
self.session = requests.session()
self.redisUtils = RedisUtils()
self.PROXYADDR = PROXYADDR
self.bcode = NOT_NEED_BCODE
self.status = CRAWL_READY
self.desc = ""
self.keyword = user.get("keyword", "")
# self.gjjaccnum = self.username if len(self.username) <= 15 else ""
# self.pwd = user.get("password", "")
self.age = FANGAGE.get(user.get('age',''),'') or FANGAGE.get(user.get('year',''), '')
self.token = user.get("token", "")
self.flower = LOUCENG.get(user.get('flower',''),'') or LOUCENG.get(user.get('floor',''),'')
self.hu_type = HUXING.get(user.get('hu_type',''),'') or HUXING.get(user.get('housetype',''),'')
# self.userid = user.get("userid", "")
self.startUrl = "http://esf.nb.fang.com/NewSecond/sale_info/searchlist_new2014.aspx"
self.hostUrl = "http://esf.nb.fang.com/"
self.result = user.get("result", "")
self.GJJInfo = []
# self.proxy = {'http':'http://143.0.188.8:80','https':'https://143.0.188.8:80'}
# 加入当次代理
# self.proxy = self._proxy()
def _proxy(self):
proxy = self.session.get(self.PROXYADDR).content
# proxy = self.session.get('http://192.168.30.185:13579/ip').content
return {"http": "http://" + proxy, "https": "http://" + proxy}
def ifNotEmptyGetIndex(self,somelist,index=0):
"""check to see it's not empty"""
if somelist:
return somelist[index]
else:
return ''
def _errhtmlRecord(self, content):
'''
错误页面保存
'''
self.logger.info("保存错页内容")
try:
filename = str(uuid.uuid1()) + ".html"
sampleDir = os.path.join(os.path.dirname(__file__), "errorHtml").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存错页内容到{0}".format(filename))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存错页出错")
self.logger.warn("{0}".format(s))
def _sampleRecord(self, filename, content):
'''
保存网页内容
'''
self.logger.info("保存网页内容")
try:
sampleDir = os.path.join(os.path.dirname(__file__), "sample/").replace("\\", "/")
os.path.exists(sampleDir) or os.mkdir(sampleDir)
with open("%s/%s" % (sampleDir, filename), 'w') as f:
f.write(content)
self.logger.debug("已保存网页内容到{0}".format(sampleDir))
except Exception:
self.status = PROGRAM_ERROR
s = traceback.format_exc()
self.logger.info("保存网页出错")
self.logger.warn("{0}".format(s))
def _fetchUrl(self, url, data=None, header=None, timeout=TIMEOUT, fileName=None, proxy=None):
'''
抓取方法
'''
self.logger.info("开始抓取 {0}".format(url))
if header:
headers = header
self.logger.debug("伪装头：{0}".format(headers))
else:
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0"}
self.logger.debug("伪装头：{0}".format(headers))
for ir in range(REQUEST_RETRY):
try:
self.logger.debug("第{0}次 抓取".format(ir))
if data:
if proxy:
content = self.session.post(url, data=data, headers=headers, timeout=timeout, allow_redirects=False, proxies=proxy)
self.logger.debug("POST url：{0}， data：{1}, proxy: {2}".format(url, data, proxy))
else:
content = self.session.post(url, data=data, headers=headers, timeout=timeout, allow_redirects=False)
self.logger.debug("POST url：{0}， data：{1}".format(url, data))
else:
if proxy:
content = self.session.get(url, headers=headers, timeout=timeout, allow_redirects=False, proxies=proxy)
self.logger.debug("GET url：{0}, proxy: {1}".format(url, proxy))
else:
content = self.session.get(url, data=data, headers=headers, timeout=timeout, allow_redirects=False)
self.logger.debug("Get url：{0}".format(url))
if fileName and SAMPLEFLAG:
self._sampleRecord(fileName, content.content)
return content
except:
self.logger.error(traceback.format_exc())
self.logger.error("request url {0} failed ,check pls".format(url))
self.status = CRAWL_TIMEOUT
raise Exception("Failed to load url (%s)" % url)
def _save_captcha(self):
"""
下载验证码，返回图片b64编码，
"""
self.logger.info("刷新验证码")
try:
codeContent = self.session.get(self.codeUrl, headers=IMGHEADERS).content
self.logger.debug("验证码二进制内容：{0}".format(codeContent)[:50])
self.logger.info("下载验证码")
self.status = NEED_BCODE
with open(os.path.join(os.path.dirname(__file__), "captcha.png").replace("\\", "/"), 'wb') as f:
f.write(codeContent)
self.logger.info("验证码图片已保存!")
bcode = base64.b64encode(codeContent)
# self.logger.debug("{}".format(bcode))
return bcode
except:
s = traceback.format_exc()
self.logger.error("刷新验证码错误：%s" % s)
return PROGRAM_ERROR, {"error": "超时或代码异常"}
def _captcha_recognize(self,imgpath):
'''
自动识别验证码
:param fileName:
:return:
'''
img = Image.open(imgpath)
for i in range(10):
code = image_to_string(img, lang='eng').encode('utf-8')
if code.isalnum() and len(code) == 4:
self.logger.info(code)
return code
self._save_captcha()
time.sleep(0.05)
def _ChioceIdent(self, flag):
'''
选择识别方式
:param flag:
:return:
'''
if flag == 'dmt':
self._save_captcha()
self.startTime = str(datetime.now())
dmt = damatuWeb.DamatuApi("huoyan2016", "123456")
# self.imageCode = dmt.decodeUrl(self.captchaId_url, 200)
self.imageCode = dmt.decode(os.path.join(os.path.dirname(__file__), "captcha.png").replace("\\", "/"), 200)
self.finishTime = str(datetime.now())
elif flag == 'input':
self._save_captcha()
pngPath = os.path.join(os.path.dirname(__file__), "captcha.png").replace("\\", "/")
self.logger.info("验证码路径：{0}".format(pngPath))
self.imageCode = raw_input("请输入验证码:")
elif flag == 'auto':
self.startTime = str(datetime.now())
self._save_captcha()
self.logger.info("识别验证码")
pngPath = os.path.join(os.path.dirname(__file__), "captcha.png").replace("\\", "/")
self.imageCode = self._captcha_recognize(pngPath)
self.logger.debug("验证码内容：{0}".format(self.imageCode))
self.finishTime = str(datetime.now())
# 返回给用户 通知redis 返回base64
elif flag == 'user':
self.startTime = datetime.now()
bcode64 = self._save_captcha()
self.redisUtils.setNotify(token=self.token, val="10",decs="需要图片验证码",result="data:image/jpg;base64,"+bcode64)
# 向session中放入数据
while True:
# 等待获取用户输入要的图片验证码值
dict_image_code = self.redisUtils.getNotify(self.token, "bcode")
if dict_image_code is not None:
self.imageCode = dict_image_code
return
else:
self.finishTime = datetime.now()
if abs(self.finishTime.minute - self.startTime.minute)>=3:
break
# 爬虫等待用户输入图片验证码超时
self.logger.warn("爬虫等待用户输入图片验证码超时:%s" % self.token)
time.sleep(1)
else:
self.status = NOT_NEED_BCODE
self.logger.info(NOT_NEED_BCODE_DESC)
def prase_detail(self, detail_content):
detail_info = etree.HTML(detail_content.text)
sum_price = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='trl-item_top']/div/i/text()"))# 总价
first_pay = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div/div[@class='trl-item_top']/div[2]/text()"))# 首付
# month_pay = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[2]/div[3]/a/div/span/i/text()"))# 月供
house_type = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[2]/div[1]/div[1]/text()")).strip()# 户型
construction_area = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[2]/div[2]/div[1]/text()"))# 建筑面积
unit_price = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[2]/div[3]/div[1]/text()"))# 单价
orientation = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[3]/div[1]/div[1]/text()"))# 朝向
floor = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[3]/div[2]/div[1]/text()"))+self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[3]/div[2]/div[2]/text()"))# 楼层
decoration = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[3]/div[3]/div[1]/text()"))# 装修
district = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='tab-cont-right']/div[4]/div[1]/div[2]/a[1]/text()"))# 小区
quyu = detail_info.xpath("//div[@id='address']/a")# 区域
quyu_list = []
for qu in quyu:
quyu_list.append(self.ifNotEmptyGetIndex(qu.xpath("text()")).strip())
area = ','.join(quyu_list) # 区域
contact_person = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@id='agantesfxq_C04_02']/text()"))# 联系人
economic_company = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='tjcont-list-cline2']/span[2]/text()"))# 经纪公司
phone = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='tjcont-list-cline3 font16']/span/text()"))# 电话
#房源信息
build_age_list = re.compile(r'<span class=\"lab\">建筑年代</span>[\s]*<span class=\"rcont\">(.*)</span>')
build_age = self.ifNotEmptyGetIndex(build_age_list.findall(str(detail_content.text)))
elevator_list = re.compile(r'<span class=\"lab\">有无电梯</span>[\s]*<span class=\"rcont\">(.*)</span>')
elevator = self.ifNotEmptyGetIndex(elevator_list.findall(str(detail_content.text)))
property_right_list = re.compile(r'<span class="lab">产权性质</span>[\s]*<span class="rcont">(.*)</span>')
property_right = self.ifNotEmptyGetIndex(property_right_list.findall(str(detail_content.text)))
category_list = re.compile(r'<span class="lab">住宅类别</span>[\s]*<span class="rcont">(.*)</span>')
category = self.ifNotEmptyGetIndex(category_list.findall(str(detail_content.text)))
build_structure_list = re.compile(r'<span class="lab">建筑结构</span>[\s]*<span class="rcont">(.*)</span>')
build_structure = self.ifNotEmptyGetIndex(build_structure_list.findall(str(detail_content.text)))
build_category_list = re.compile(r'<span class="lab">建筑类别</span>[\s]*<span class="rcont">(.*)</span>')
build_category = self.ifNotEmptyGetIndex(build_category_list.findall(str(detail_content.text)))
list_time_list = re.compile(r'<span class="lab">挂牌时间</span>[\s]*<span class="rcont">[\s]*(.*)[\s]*.*</span>')
list_time = self.ifNotEmptyGetIndex(list_time_list.findall(str(detail_content.text))).strip()
fang_info = self.ifNotEmptyGetIndex(detail_info.xpath("//div[@class='content-item'][2]/div[2]/div/div/div/text()")) # 房源描述
# 小区信息
reference_price = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div/div[1]/span[2]/i/text()"))#参考均价
district_than_year = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div/div[2]/span[2]/em/span/text()")) # 同比去年
district_than_month = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div/div[3]/span[2]/em/span/text()")) # 环比上月
district_property_type = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[1]/span[2]/text()")).strip() # 物业类型
district_property_costs = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[2]/span[2]/text()")).strip() # 物业费用
district_build_type = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[3]/span[2]/text()")).strip() # 建筑类型
district_build_age = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[4]/span[2]/text()")).strip() # 建筑年代
district_green_rate = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[5]/span[2]/text()")).strip() # 绿化率
district_volume_tate = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[6]/span[2]/text()")).strip() # 容积率
district_diversion = self.ifNotEmptyGetIndex(detail_info.xpath("//*[@class='cont pt30']/div[2]/div[7]/span[2]/text()")).strip() # 人车分流
self.GJJInfo.append(hypc_soufun.baseinfo(
sum_price=sum_price,
first_pay=first_pay,
house_type=house_type,
construction_area=construction_area,
unit_price=unit_price,
orientation=orientation,
floor=floor,
decoration=decoration,
district=district,
area=area,
contact_person=contact_person,
economic_company=economic_company,
phone=phone,
build_age=build_age,
elevator=elevator,
property_right=property_right,
category=category,
build_structure=build_structure,
build_category=build_category,
list_time=list_time,
fang_info=fang_info,
reference_price=reference_price,
district_than_year=district_than_year,
district_than_month=district_than_month,
district_property_type=district_property_type,
district_property_costs=district_property_costs,
district_build_type=district_build_type,
district_build_age=district_build_age,
district_green_rate=district_green_rate,
district_volume_tate=district_volume_tate,
district_diversion=district_diversion,
))
def login(self,flag):
# self._ChioceIdent(flag)
'''there are divided into bulk and real time'''
if self.keyword:
LoginData = {
'input_keyw1':self.keyword,
'city':'宁波',
'district':'',
'purpose':'סլ',
'room':'',
'pricemin':'',
'pricemax':'',
'trackLine':'',
'keyword':self.keyword,
'renttype':'',
'strCity':'宁波',
'strDistrict':'',
'Strprice':'',
'StrNameKeyword':self.keyword,
'houseType':'',
'isnewhouse':0,
'isFinder':0,
'fromdianshang':'',
'fromhouseprom':'',
'fromesfchengjiao':''
}
# content = self._fetchUrl(url=self.startUrl, header=LOGINHEADERS, proxy=self.proxy, data=LoginData, fileName="login.html")
content = self._fetchUrl(url=self.startUrl, header=LOGINHEADERS, data=LoginData, fileName="login.html")
return content
else:
# content = self._fetchUrl(url=self.hostUrl, header=PERHEADERS, proxy=self.proxy, fileName="login.html")
content = self._fetchUrl(url=self.hostUrl, header=PERHEADERS, fileName="login.html")
return content
@Time()
def crawl(self, flag=""):
CurTime = datetime.now().strftime("%Y-%m-%d")
PastTime = (datetime.now() - timedelta(days=729)).strftime("%Y-%m-%d")
try:
# login
# for i in range(10):
content = self.login(flag)
# try:
if 'keyword=' not in content.text.encode('utf8') and content.text.encode('utf8'):
self.logger.info("获取信息成功：%s"%'good info')
secondUrl = 'http://esf.nb.fang.com/house/'+self.hu_type+self.flower+self.age+'kw'+'/'
# content = self._fetchUrl(url=secondUrl, header=PERHEADERS, proxy=self.proxy, fileName="person.html")
content = self._fetchUrl(url=secondUrl, header=PERHEADERS, fileName="person.html")
infohtml = etree.HTML(content.text)
num_info = str(self.ifNotEmptyGetIndex(infohtml.xpath("//div[@class='fanye gray6']/span/text()")).encode('utf8'))
if num_info:
zong = re.compile(r'共(\d*)页')
num = zong.search(num_info).group(1)#提取页数
for i in range(int(num)):
# proxy1 = self._proxy()
fang_url = 'http://esf.nb.fang.com/house/'+self.hu_type+self.flower+self.age+'i3'+str(i+1)+'-'+'kw'+'/'
# list_content = self._fetchUrl(url=fang_url, header=PERHEADERS, proxy=self.proxy, fileName="list.html")
list_content = self._fetchUrl(url=fang_url, header=PERHEADERS, fileName="list.html")
list_info = etree.HTML(list_content.text)
html = list_info.xpath("//div[@class='houseList']/dl")
for ht in html[:-1]:
a = self.ifNotEmptyGetIndex(ht.xpath("dd[@class='info rel floatr']/p[1]/a/@href"))
if a:
detail_url = 'http://esf.nb.fang.com' + str(a)
# 具体的房产页信息
detail_content = self._fetchUrl(url=detail_url, header=PERHEADERS, fileName="detail.html")
self.prase_detail(detail_content)
self.status= CRAWL_SUCCESS
self.result.append(self.GJJInfo)
# a = json.dumps(self.result[0],ensure_ascii=False)
# print a
# except:
elif not content.text.encode('utf8'):
self.logger.info("获取信息成功：%s"%content)
# data = urllib.quote(self.keyword.decode(sys.stdin.encoding).encode('gb2312'))
data = urllib.quote(self.keyword.decode('utf-8').encode('gb2312'))
secondUrl = 'http://esf.nb.fang.com/house/'+self.hu_type+self.flower+self.age+'kw'+data.lower()+'/'
# content = self._fetchUrl(url=secondUrl, header=PERHEADERS, proxy=self.proxy, fileName="person.html")
content = self._fetchUrl(url=secondUrl, header=PERHEADERS, fileName="person.html")
infohtml = etree.HTML(content.text)
num_info = str(self.ifNotEmptyGetIndex(infohtml.xpath("//div[@class='fanye gray6']/span/text()")).encode('utf8'))
if num_info:
zong = re.compile(r'共(\d*)页')
num = zong.search(num_info).group(1)#提取页数
for i in range(int(num)):
# proxy1 = self._proxy()
fang_url = 'http://esf.nb.fang.com/house/'+self.hu_type+self.flower+self.age+'i3'+str(i+1)+'-'+'kw'+data.lower()+'/'
# list_content = self._fetchUrl(url=fang_url, header=PERHEADERS, proxy=self.proxy, fileName="list.html")
list_content = self._fetchUrl(url=fang_url, header=PERHEADERS, fileName="list.html")
list_info = etree.HTML(list_content.text)
html = list_info.xpath("//div[@class='houseList']/dl")
for ht in html:
a = self.ifNotEmptyGetIndex(ht.xpath("dd[@class='info rel floatr']/p[1]/a/@href"))
if a:
detail_url = 'http://esf.nb.fang.com' + str(a)
# 具体的房产页信息
detail_content = self._fetchUrl(url=detail_url, header=PERHEADERS, fileName="detail.html")
self.prase_detail(detail_content)
self.status= CRAWL_SUCCESS
else:
self.status= CRAWL_SUCCESS
self.GJJInfo.append(hypc_soufun.baseinfo())
self.result.append(self.GJJInfo)
# a = json.dumps(self.result[0],ensure_ascii=False)
# print a
else:
self.logger.info("信息失败：%s" % 'bad info')
self.logger.info(IDCARD_ERROR_DESC)
self.status, self.desc = IDCARD_ERROR, IDCARD_ERROR_DESC
self.result.append(self.GJJInfo)
# break
except:
s = traceback.format_exc()
self.logger.error("抓取错误：%s" % s)
self.status, self.desc = self.status, PROGRAM_ERROR_DESC
finally:
try:
if len(self.result) == 1 and self.status == CRAWL_SUCCESS:
self.desc = CRAWL_SUCCESS_DESC
# print self.result
result_json = json.dumps(self.result[0], ensure_ascii=False)
# print result_json
self.redisUtils.setNotify(type=TYPEVALUE,token=self.token, val="1", decs="抓取成功！", result=result_json)
# self.push_data(TYPEVALUE, self.userid, result_json)
elif self.status == CRAWL_FAIL:
self.desc = CRAWL_FAIL_DESC
elif self.status == CRAWL_TIMEOUT:
self.desc = CRAWL_TIMEOUT_DESC
elif self.status == IDCARD_ERROR:
self.desc = IDCARD_ERROR_DESC
elif self.status == PASSWORD_ERROR:
self.desc = PASSWORD_ERROR_DESC
elif self.status == BCODE_ERROR:
self.desc = BCODE_ERROR_DESC
else:
self.desc = PROGRAM_ERROR_DESC
except Exception as e:
s = traceback.format_exc()
self.logger.error(s)
finally:
try:
self.redisUtils.setNotify(type=TYPEVALUE, token=self.token, val=self.status, decs=self.desc)
except Exception:
s = traceback.format_exc()
self.logger.error(s)
def zipToStr(self, content):
'''
使用urllib2获取到的内容被压缩，需要进行解压缩
:param content: 需要解压的内容
:return:
'''
try:
conn = zlib.decompress(content, 16 + zlib.MAX_WBITS)
return conn
except:
self.logger.error('解压缩响应内容出错%s' % traceback.format_exc())
raise Exception("解压缩响应内容出错%s" % traceback.format_exc())
