class TestMysql(object):
if __name__ == "__main__":
os.environ['browser'] = "172.17.161.230"
os.environ['port'] = '8912'
webdriver = WebDriver()
driver = webdriver.get_chrome()
driver.set_window_size(1920, 1080)
# 打开登录页面
driver.get('https://www.qichacha.com/user_login')
# 单击用户名密码登录的标签
tag = driver.find_element_by_xpath('//*[@id="normalLogin"]')
tag.click()
# 将用户名、密码注入
driver.find_element_by_id('nameNormal').send_keys('13811668973')
driver.find_element_by_id('pwdNormal').send_keys('Abcd1234')
time.sleep(10) # 休眠，人工完成验证步骤，等待程序单击“登录”
# 单击登录按钮
btn = driver.find_element_by_xpath(
'//*[@id="user_login_normal"]/button')
btn.click()
time.sleep(10)
source = driver.page_source
driver.find_element_by_id("searchkey").send_keys("京东")
driver.find_element_by_id("V3_Search_bt").click()
source = driver.page_source
print(source)
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://www.paycircle.cn/company/search.php?kw=" + urllib.parse.quote(
keyword) + "&c=SearchList&"
if driver is None:
senti_util.log_error("支付圈", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
source = driver.page_source
senti_util.snapshot_home("支付圈", url, batch_num, website, driver)
soup = BeautifulSoup(source, 'html.parser')
div_list = soup.find_all(attrs={'class': 'list'})
if div_list.__len__() > 0:
news = div_list[0].find_all('tr')
for new in news:
href = new.find_all('td')[2].find_all('a')[0].get("href")
content = new.find_all('td')[2].find_all(
'li')[1].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text("支付圈", content, href,
batch_num, website)
else:
logger.info("支付圈没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(website_name, merchant_name, batch_num):
try:
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "https://www.p2peye.com/search.php?mod=zonghe&srchtxt=" + urllib.parse.quote(website_name)
driver.get(url)
source = driver.page_source
senti_util.snapshot_home("网贷天眼", merchant_name, url,
batch_num, driver)
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all(attrs={'class': 'result-t'})
if news.__len__() > 0:
for new in news:
href = new.find_all('a')[0].get("href")
content = new.get_text()
if content.find(website_name) != -1:
senti_util.senti_process_text("网贷天眼", merchant_name,content, "http://" + href[2:],
batch_num)
else:
logger.info("网贷天眼没有搜索到数据: %s", merchant_name)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(website_name, merchant_name, batch_num):
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path=chromedriver_path)
"""
try:
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://www.chinaft.com.cn/news/search/_1.shtml?key=" + urllib.parse.quote(
website_name)
driver.get(url)
source = driver.page_source
senti_util.snapshot_home("交易中国", merchant_name, url, batch_num,
driver)
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all("div",
attrs={'class': 'xixi_ChinaFT_left_news_box'})
if news.__len__() > 0:
for new in news:
if not gl.check_by_batch_num(batch_num):
break
href = new.find_all('a')[1].get("href")
content = new.find_all('a')[1].get_text()
if content.find(website_name) != -1:
senti_util.senti_process_text(
"交易中国", merchant_name, content,
"http://www.chinaft.com.cn" + href, batch_num)
else:
logger.info("交易中国没有搜索到数据: %s", merchant_name)
except Exception as e:
logger.error(e)
finally:
driver.quit()
class TestWangdaitianyan(object):
if __name__ == "__main__":
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path="C:/chromedriver_2.38/chromedriver.exe")
driver.get("https://www.wdzj.com/front/search/index?key=" + urllib.parse.quote("猫小贷"))
"""
try:
driver = WebDriver.get_chrome()
driver.get("http://www.wdzj.com/news/yc/2934681.html")
except Exception as e: # 异常处理
print(e)
pass
SnapshotService.create_snapshot(driver)
time.sleep(5)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
print(soup.find_all("ul", attrs={'class': 'so-tzbox'}))
news = soup.find_all("ul", attrs={'class':
'so-tzbox'})[0].find_all("li")
if news.__len__() > 0:
for new in news:
href = new.find_all('a')[0].get("href")
print(href[2:])
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://paynews.net/search.php?mod=forum"
if driver is None:
senti_util.log_error("支付产业网", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
search_text_blank = driver.find_element_by_id("scform_srchtxt")
search_text_blank.send_keys(keyword)
search_text_blank.send_keys(Keys.RETURN)
senti_util.snapshot_home("支付产业网", url, batch_num, website, driver)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
div_list = soup.find(attrs={'class': 'slst mtw'})
if div_list is not None and div_list.__len__() > 0:
news = div_list.find_all('li')
for new in news:
href = new.find_all('a')[0].get("href")
content = new.find_all('a')[0].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text(
"支付产业网", content, "http://paynews.net/" + href,
batch_num, website)
else:
logger.info("支付产业网没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "https://tousu.sina.com.cn/index/search/?keywords=" + urllib.parse.quote(keyword) + "&t=0"
if driver is None:
senti_util.log_error("黑猫投诉", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
source = driver.page_source
senti_util.snapshot_home("黑猫投诉", url, batch_num, website, driver)
soup = BeautifulSoup(source, 'html.parser')
items = soup.find_all(attrs={'class': 'blackcat-con'})
if items.__len__() > 0:
for item in items:
href = item.find_all('a')[0].get("href")
content = item.find_all('h1')[0].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text("黑猫投诉", content, href,
batch_num, website)
else:
logger.info("黑猫投诉没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
class TestWangdaitianyan(object):
if __name__ == "__main__":
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path="C:/chromedriver_2.38/chromedriver.exe")
driver.get("http://www.chinaft.com.cn/news/search/_1.shtml?key=" + urllib.parse.quote("京东"))
"""
driver = WebDriver.get_chrome()
try:
driver.get("http://www.chinaft.com.cn/news/search/_1.shtml?key=" +
urllib.parse.quote("京东"))
except Exception as e:
print("error")
pass
print("e")
SnapshotService.create_snapshot(driver)
time.sleep(5)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all("div",
attrs={'class': 'xixi_ChinaFT_left_news_box'})
if news.__len__() > 0:
for new in news:
href = new.find_all('a')[1].get("href")
print("http://www.chinaft.com.cn" + href)
print(new.find_all('a')[1].get_text())
def get_access_res(url):
driver = WebDriver.get_chrome_for_access()
try:
if str(url).startswith("http"):
http_url = str(url)
else:
http_url = "http://" + str(url)
logger.info("http_url: %s", http_url)
driver.get(http_url)
title = driver.title
source = driver.page_source
if title.__contains__('404') or source.__contains__(
'ERR_NAME_NOT_RESOLVED') or source.__contains__(
'ERR_CONNECTION_REFUSED') or source.__contains__(
'ERR_CONNECTION_TIMED_OUT') or source.__contains__(
'ERR_NAME_NOT_RESOLVED') or source.__contains__(
'ERR_NAME_RESOLUTION_FAILED') or source.__contains__(
'DNS_PROBE_FINISHED_NXDOMAIN') or source.__contains__(
'ERR_EMPTY_RESPONSE') or source.__contains__(
'主机开设成功') or source.__contains__(
'非法阻断') or source.__contains__(
'Bad Request') or source.__contains__(
'404 page not found') or source.__contains__('https://wanwang.aliyun.com/domain/parking'):
return None, http_url
else:
return http_url, driver.current_url
except Exception as e:
logger.error(e)
return None, None
finally:
driver.quit()
class TestWangdaitianyan(object):
if __name__ == "__main__":
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path="C:/chromedriver_2.38/chromedriver.exe")
driver.get("https://www.baidu.com/")
driver.find_element_by_id("kw").send_keys(u"京东")
driver.find_element_by_id("su").click()
"""
driver = WebDriver.get_chrome()
try:
driver.get("https://www.baidu.com/")
driver.find_element_by_xpath('//input[@name="wd"]').send_keys(u"京东")
except Exception as e: # 异常处理
print(e)
pass
SnapshotService.create_snapshot(driver)
time.sleep(5)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
for result_table in soup.find_all('h3', class_='t'):
a_click = result_table.find("a");
print(a_click.get_text()) # 标题
print(str(a_click.get("href"))) # 链接
'''
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = 'https://baike.baidu.com/item/%s' % urllib.parse.quote(keyword)
if driver is None:
senti_util.log_error("百度百科", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
check_exist = soup.find_all(
name='p', attrs={'class': re.compile('sorryCont')})
if check_exist.__len__() == 0:
description = soup.find(
attrs={"name": "description"})['content']
senti_util.senti_process_text("百度百科", description, url,
batch_num, website)
else:
senti_util.snapshot_home("百度百科", url, batch_num, website,
driver)
logger.info("百度百科没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(keyword, website_name, batch_num, merchant_name, merchant_num):
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path=chromedriver_path)
"""
driver = WebDriver.get_chrome()
try:
senti_util = SentiUtil()
url = "http://tieba.baidu.com/f?fr=wwwt&kw=" + urllib.parse.quote(
keyword)
driver.get(url)
senti_util.snapshot_home("百度贴吧", website_name, url, batch_num,
merchant_name, merchant_num, driver)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all(
"div", attrs={'class': 'threadlist_title pull_left j_th_tit '})
if news.__len__() > 0:
for new in news:
href = new.find_all('a')[0].get("href")
content = new.find_all('a')[0].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text(
"百度贴吧", website_name, content,
"http://tieba.baidu.com" + href, batch_num,
merchant_name, merchant_num)
else:
logger.info("百度贴吧没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://wenshu.court.gov.cn/"
if driver is None:
senti_util.log_error("黑猫投诉", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
search_text_blank = driver.find_element_by_xpath(
"//*[@class='searchKey search-inp']")
search_text_blank.send_keys(keyword)
search_text_blank.send_keys(Keys.RETURN)
time.sleep(3)
source = driver.page_source
senti_util.snapshot_home("裁判文书网", url, batch_num, website, driver)
soup = BeautifulSoup(source, 'html.parser')
for a_tag in soup.find_all('a', class_='caseName'):
href = a_tag.get("href")
title = a_tag.get_text()
if title.find(keyword) != -1:
senti_util.senti_process_text(
"裁判文书网", title,
"http://wenshu.court.gov.cn/website/wenshu" + href[2:],
batch_num, website)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
class TestWangdaitianyan(object):
if __name__ == "__main__":
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path="C:/chromedriver_2.38/chromedriver.exe")
driver.get("http://www.wangdaibus.com/search.php?mod=forum")
driver.find_element_by_id("scform_srchtxt").send_keys(u"京东")
driver.find_element_by_id("scform_submit").click()
"""
driver = WebDriver.get_chrome()
try:
driver.get(
"http://www.wangdaibus.com/search/list?subject=%E4%BA%AC%E4%B8%9C"
)
aaa = "京东"
#lement_by_xpath('//input[@name="subject"]').send_keys(aaa)
#driver.find_element_by_xpath('//input[@name="subject"]').send_keys(Keys.ENTER)
time.sleep(10)
except Exception as e: # 异常处理
logger.error(e)
pass
SnapshotService.create_snapshot(driver)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all("h3", attrs={'class': 'xs3'})
if news.__len__() > 0:
for new in news:
href = new.find_all('a')[0].get("href")
logger.info("http://www.wangdaibus.com/" + href)
logger.info(new.get_text())
'''
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "https://www.baidu.com/"
if driver is None:
senti_util.log_error("百度搜索", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
search_text_blank = driver.find_element_by_id("kw")
search_text_blank.send_keys(keyword)
search_text_blank.send_keys(Keys.RETURN)
time.sleep(5)
# driver.find_element_by_xpath('//input[@name="wd"]').send_keys(website_name)
senti_util.snapshot_home("百度搜索", url, batch_num, website, driver)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
for result_table in soup.find_all('h3', class_='t'):
a_click = result_table.find("a")
title = a_click.get_text()
if title.find(keyword) != -1:
senti_util.senti_process_text("百度搜索", title, str(a_click.get("href")),
batch_num, website)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://ts.21cn.com/home/search?keyword=" + urllib.parse.quote(
keyword)
if driver is None:
senti_util.log_error("聚投诉", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
driver.implicitly_wait(3)
source = driver.page_source
senti_util.snapshot_home("聚投诉", url, batch_num, website, driver)
soup = BeautifulSoup(source, 'html.parser')
items = soup.find_all(attrs={'class': 'complain-item'})
if items.__len__() > 0:
for item in items:
href = item.find_all('a')[1].get("href")
content = item.find_all('a')[1].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text(
"聚投诉", content,
"http://www.paycircle.cn" + href[1:], batch_num,
website)
else:
logger.info("聚投诉没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def senti_process_text(platform, text, href, batch_num, website):
driver = WebDriver.get_chrome()
keyword_dao = KeywordDao()
monitor_third_dao = MonitorThirdDao()
# 截图
try:
driver.get(href)
snapshot = SnapshotService.create_snapshot(driver, batch_num,
website, '舆情')
is_normal = "正常"
keywords = keyword_dao.get_all()
for keyword in keywords:
index = text.find(keyword.name)
monitor_third = MonitorThird()
monitor_third.website_name = website.website_name
monitor_third.merchant_num = website.merchant_num
monitor_third.merchant_name = website.merchant_name
monitor_third.domain_name = website.domain_name
monitor_third.saler = website.saler
monitor_third.batch_num = batch_num
monitor_third.url = href
monitor_third.type = platform
if index != -1:
is_normal = "异常"
monitor_third.is_normal = is_normal
monitor_third.level = '高'
monitor_third.outline = '检测到敏感词：' + str(keyword.name)
monitor_third.snapshot = snapshot
monitor_third_dao.add(monitor_third)
else:
pass
if is_normal == "正常":
if platform == "百度百科":
monitor_third.level = '-'
monitor_third.outline = '-'
monitor_third.is_normal = is_normal
monitor_third.snapshot = snapshot
monitor_third_dao.add(monitor_third)
pass
except ConnectionError as conn_error:
logger.error(conn_error)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def simulation_404(url):
timestamp = str(time.time())
snapshot = timestamp + ".png"
path = ims_rest_base + "/views/system/404.jsp?url=" + str(url)
img_404 = base_filepath + "/" + timestamp
try:
driver = WebDriver.get_chrome()
driver.get(path)
driver.save_screenshot(img_404 + ".png")
im = Image.open(img_404 + ".png")
im_resize = im.resize((50, 50), Image.ANTIALIAS)
im_resize.save(img_404 + "_thumb.bmp")
except Exception as e:
logger.info(e)
return snapshot
finally:
driver.quit()
return snapshot
def inspect(batch_num, url, website):
monitor_bc_dao = MonitorBcDao()
monitor_bc = MonitorBc()
monitor_bc.batch_num = batch_num
monitor_bc.domain_name = website.domain_name
monitor_bc.merchant_num = website.merchant_num
monitor_bc.website_name = website.website_name
monitor_bc.merchant_name = website.merchant_name
monitor_bc.saler = website.saler
monitor_bc.is_normal = '正常'
monitor_bc.kinds = '工商巡检'
monitor_bc.outline = '企业工商信息检查正常'
monitor_bc.level = '-'
url = ims_rest_base + "open/api/v1/agent/monitor_bc"
data_json = {
"merchantNum": website.merchant_num,
"merchantName": website.merchant_name
}
data = bytes(parse.urlencode(data_json), encoding="utf8")
new_url = request.Request(url, data)
res = request.urlopen(new_url).read().decode('utf-8')
bc_response = json.loads(res)
if bc_response['status'] is True:
logger.info("企业工商信息检测正常：%s", website.merchant_name)
else:
logger.info("企业工商信息检测异常：%s", website.merchant_name)
monitor_bc.is_normal = '异常'
monitor_bc.kinds = '企业工商信息'
monitor_bc.outline = bc_response['msg']
monitor_bc.level = '高'
url = ims_rest_base + "views/system/qichacha.jsp?merchantNum=" + website.merchant_num
driver = WebDriver.get_phantomjs()
try:
logger.info("企业工商信息截图：%s", website.merchant_name)
driver.get(url)
snapshot = SnapshotService.create_snapshot(driver, batch_num,
website, "工商巡检")
monitor_bc.snapshot = snapshot
monitor_bc_dao.add(monitor_bc)
except Exception as e:
print(e)
monitor_bc_dao.add(monitor_bc)
finally:
driver.quit()
def monitor(website_name, merchant_name, batch_num):
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path=chromedriver_path)
"""
try:
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "https://www.wdzj.com/front/search/index?key=" + urllib.parse.quote(
website_name)
driver.get(url)
source = driver.page_source
senti_util.snapshot_home("网贷之家", merchant_name, url, batch_num,
driver)
soup = BeautifulSoup(source, 'html.parser')
tzbox = soup.find_all("ul", attrs={'class': 'so-tzbox'})
if tzbox.__len__() == 0:
return
news = tzbox[0].find_all("li")
if news.__len__() > 0:
for new in news:
if not gl.check_by_batch_num(batch_num):
break
href = new.find_all('a')[0].get("href")
content = new.get_text()
if content.find(website_name) != -1:
senti_util.senti_process_text("网贷之家", merchant_name,
content,
"http://" + href[2:],
batch_num)
else:
logger.info("网贷之家没有搜索到数据: %s", merchant_name)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def monitor(website_name, merchant_name, batch_num):
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options,
executable_path=chromedriver_path)
"""
try:
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://www.wangdaibus.com/search/list?subject=" + urllib.parse.quote(
website_name)
driver.get(url)
time.sleep(10)
senti_util.snapshot_home("网贷巴士", merchant_name, url, batch_num,
driver)
# driver.find_element_by_xpath('//input[@name="srchtxt"]').send_keys(website_name)
# driver.find_element_by_xpath('//input[@name="srchtxt"]').send_keys(Keys.ENTER)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
news = soup.find_all("h3", attrs={'class': 'xs3'})
if news.__len__() > 0:
for new in news:
if not gl.check_by_batch_num(batch_num):
break
href = new.find_all('a')[0].get("href")
content = new.get_text()
if content.find(website_name) != -1:
senti_util.senti_process_text(
"网贷巴士", merchant_name, content,
"http://www.wangdaibus.com/" + href, batch_num)
else:
logger.info("网贷巴士没有搜索到数据: %s", merchant_name)
except Exception as e:
logger.error(e)
return
finally:
driver.quit()
def snapshot_qichacha(batch_num, url, website):
timestamp = int(time.time())
snapshot = batch_num + "_" + website.merchant_name + "_" + website.merchant_num + "_工商_" + str(
timestamp) + ".png"
path = base_filepath + "/" + batch_num + "_" + website.merchant_name + "_" + website.merchant_num + "_工商_" + str(
timestamp)
try:
driver = WebDriver.get_chrome_by_local()
# driver = webdriver.Chrome(executable_path='/usr/bin/chromedriver',
# desired_capabilities=dcap,
# options=chrome_options)
driver.set_page_load_timeout(60)
driver.set_script_timeout(60)
driver.maximize_window()
driver.get(url)
driver.save_screenshot(path + ".png")
img = Image.open(path + ".png")
jpg = img.crop((265, 158, 420, 258))
jpg.save(path + "_thumb.bmp")
return driver, snapshot
except Exception as e:
logger.info(e)
return None, None
def monitor(keyword, batch_num, website):
driver = WebDriver.get_chrome()
senti_util = SentiUtil()
url = "http://www.zhifujie.com/search/search"
if driver is None:
senti_util.log_error("支付界", url, batch_num, website)
return
else:
pass
try:
driver.get(url)
search_text_blank = driver.find_element_by_id("searchbox")
search_text_blank.send_keys(keyword)
driver.find_element_by_xpath(
'//button[contains(text(), "搜索")]').click()
time.sleep(5)
source = driver.page_source
senti_util.snapshot_home("支付界", url, batch_num, website, driver)
soup = BeautifulSoup(source, 'html.parser')
items = soup.find_all(attrs={'class': 'main-news-content-item'})
if items.__len__() > 0:
for item in items:
href = item.find_all('a')[1].get("href")
content = item.find_all('a')[1].get_text()
if content.find(keyword) != -1:
senti_util.senti_process_text(
"支付界", content,
"http://www.paycircle.cn" + href[1:], batch_num,
website)
else:
logger.info("支付界没有搜索到数据: %s", keyword)
except Exception as e:
logger.error(e)
senti_util.snapshot_home("支付界", url, batch_num, website, driver)
return
finally:
driver.quit()
def get_proxy_access_res(url):
if str(url).startswith("http"):
http_url = str(url)
else:
http_url = "http://" + str(url)
driver = WebDriver.get_proxy_chrome()
if driver is None:
return None, None
else:
try:
logger.info("http_url: %s", http_url)
driver.get(http_url)
title = driver.title
if title.__contains__('404') or driver.page_source.__contains__(
'ERR_NAME_NOT_RESOLVED') or driver.page_source.__contains__(
'ERR_CONNECTION_REFUSED') or driver.page_source.__contains__('ERR_CONNECTION_TIMED_OUT'):
return None, http_url
else:
return http_url, driver.current_url
except Exception as e:
logger.error(e)
return None, None
finally:
driver.quit()
def inspect(batch_num, url, website, task_id):
monitor_bc_dao = MonitorBcDao()
monitor_bc = MonitorBc()
monitor_bc.batch_num = batch_num
monitor_bc.domain_name = website.domain_name
monitor_bc.merchant_num = website.merchant_num
monitor_bc.website_name = website.website_name
monitor_bc.merchant_name = website.merchant_name
monitor_bc.saler = website.saler
monitor_bc.is_normal = '正常'
monitor_bc.kinds = '工商巡检'
monitor_bc.outline = '企业工商信息检查正常'
monitor_bc.level = '-'
url = ims_rest_base + "open/api/v1/agent/monitor_bc"
data_json = {
"merchantNum": website.merchant_num,
"merchantName": website.merchant_name,
"taskId": task_id,
"batchNum": batch_num
}
data = bytes(parse.urlencode(data_json), encoding="utf8")
new_url = request.Request(url, data)
res = request.urlopen(new_url).read().decode('utf-8')
logger.info("res：%s", res)
bc_response = json.loads(res)
logger.info("bc_response：%s", bc_response)
if bc_response['isNormal'] == "正常":
monitor_bc.status = bc_response['businessInfo']['enterpriseBase'][
'entStatus']
logger.info("企业工商信息检测正常：%s", website.merchant_name)
elif bc_response['isNormal'] == "无法获取":
logger.info("企业工商信息检测无法获取：%s", website.merchant_name)
monitor_bc.is_normal = '无法获取'
monitor_bc.status = bc_response['status']
monitor_bc.outline = bc_response['msg']
monitor_bc.outline = '企业工商信息无法获取,跳过巡检。'
else:
logger.info("企业工商信息检测异常：%s", website.merchant_name)
monitor_bc.is_normal = '异常'
monitor_bc.kinds = '企业工商信息'
monitor_bc.outline = bc_response['msg']
enterpriseBase = bc_response['businessInfo']['enterpriseBase']
if enterpriseBase is None:
monitor_bc.status = bc_response['status']
else:
monitor_bc.status = bc_response['businessInfo'][
'enterpriseBase']['entStatus']
monitor_bc.level = '高'
url = ims_rest_base + "views/system/enterprise.jsp?merchantNum=" + website.merchant_num
driver = WebDriver.get_phantomjs()
try:
logger.info("企业工商信息截图：%s", website.merchant_name)
driver.get(url)
snapshot = SnapshotService.create_snapshot(driver, batch_num,
website, "工商巡检")
monitor_bc.snapshot = snapshot
monitor_bc_dao.add(monitor_bc)
except Exception as e:
print(e)
monitor_bc_dao.add(monitor_bc)
finally:
driver.quit()
def gather_urls(self, website_id, uri, website_name, domain_name,
merchant_name, merchant_num, saler, level):
strategy_service = StrategyService()
strategy = strategy_service.get_strategy()
frequency = strategy.frequency
if strategy.frequency == 0 or strategy.frequency is None:
logger.info("未设置爬取频率限制,继续执行任务..")
else:
logger.info("爬取频率限制为:%s 秒", strategy.frequency)
time.sleep(frequency)
if level == 1:
logger.info("gather url just to 3 level: %s ", domain_name)
return
logger.info("gather url for website: %s ", uri)
weburl_dao = WeburlDao()
try:
driver = WebDriver.get_chrome_for_urlgather()
driver.get(uri)
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
for k in soup.find_all('a'):
href = str(k.get('href'))
logger.info("origin href: %s", href)
if href.endswith(".jpg") or href.endswith(
".jpeg"
) or href.endswith(".bmp") or href.endswith(
".png"
) or href.endswith(
".swf"
) or href == '/' or href == 'http://' or href == '#' or href.startswith(
'javascript') or href == 'None' or href.startswith(
'tencent://'):
continue
elif href.startswith('http://') or href.startswith('https://'):
href = href
elif href.startswith('/'):
href = uri + href
elif href.startswith('./'):
href = uri + href[1:]
else:
href = uri + "/" + href
url = href.replace("//",
"/").replace("/../",
"/").replace(":/", "://")
logger.info("href %s", href)
logger.info("url %s", url)
title = soup.find('title').string
weburl = Weburl(
website_id=website_id,
website_name=website_name,
merchant_name=merchant_name,
merchant_num=merchant_num,
saler=saler,
title=title,
type='page',
parent=uri,
url=url.replace("http:/http:/", "http://").replace(
"http:/https:/",
"https://").replace("https:/http:/", "https://"))
weburl_dao.add(weburl)
# self.gather_urls(website_id, href, website_name, domain_name, level + 1)
except Exception as e:
logger.error(e)
def monitor(task_id, status):
ims_api = ImsApi()
tracking_dao = TrackingDetailDao()
strategy_service = StrategyService()
strategy = strategy_service.get_strategy()
tracking_details = tracking_dao.get_by_task(task_id, status)
if tracking_details.__len__() > 0:
for tracking_detail in tracking_details:
if gl.get_value('TRACKING_STATUS'):
pass
else:
logger.info("快递单任务已停止，任务id：%s", task_id)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
ims_api.done_tracking(task_id)
return
if strategy.frequency == 0 or strategy.frequency is None:
logger.info("未设置爬取频率限制,继续执行任务..")
else:
logger.info("爬取频率限制为:%s 秒", strategy.frequency)
time.sleep(strategy.frequency)
random_seconds = random.randint(10, 15)
logger.info("快递单检测随机等待 %s 秒...", str(random_seconds))
time.sleep(random_seconds)
tracking_detail.start_time = datetime.datetime.now()
tracking_detail.status = "done"
logger.info("准备检查单号:%s ", tracking_detail.tracking_num)
url = "https://www.trackingmore.com/cn/" + tracking_detail.tracking_num
logger.info("url:%s ", url)
driver = WebDriver.get_phantomjs()
try:
driver.get(url)
except Exception as e:
logger.error(e)
tracking_detail.result = "true"
tracking_detail.des = "检测超时,建议手动验证:" + url
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = url
tracking_detail.snapshot = ""
tracking_dao.update(tracking_detail)
logger.info("单号巡检发生异常，跳过")
driver.quit()
continue
try:
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
snapshot = SnapshotService.snapshot_tracking(
driver, tracking_detail)
a_tags = soup.find_all("a", attrs={'class': 'ulliselect'})
has_tracking = False
if a_tags.__len__() > 0:
for a_tag in a_tags:
if a_tag.get_text().strip(
) == tracking_detail.tracking_name:
has_tracking = True
url = "http:" + a_tag.get("href")
driver.get(url)
snapshot = SnapshotService.snapshot_tracking(
driver, tracking_detail)
try:
source = driver.page_source
soup = BeautifulSoup(source, 'html.parser')
items = soup.find_all(
attrs={
'class': 'line-gutter-backdrop'
})
# 异常为0
if items.__len__() != 0:
tracking_detail.result = "false"
tracking_detail.des = "爬虫请求疑似被拦截，建议手动验证!"
tracking_detail.end_time = datetime.datetime.now(
)
tracking_detail.url = url
tracking_detail.snapshot = snapshot
else:
soup = BeautifulSoup(
source, 'html.parser')
item_length = soup.find_all(
"li",
attrs={
'class': 's-packStatst'
}).__len__()
if item_length > 0:
tracking_detail.result = "true"
tracking_detail.des = "物流正常"
tracking_detail.end_time = datetime.datetime.now(
)
tracking_detail.url = url
tracking_detail.snapshot = snapshot
else:
tracking_detail.result = "false"
tracking_detail.des = "没有查询到物流信息"
tracking_detail.end_time = datetime.datetime.now(
)
tracking_detail.url = url
tracking_detail.snapshot = snapshot
except Exception as e:
print(e)
# 正常
tracking_detail.result = "false"
tracking_detail.des = "检测疑似异常，建议手动验证！"
tracking_detail.end_time = datetime.datetime.now(
)
tracking_detail.url = url
tracking_detail.snapshot = snapshot
break
else:
continue
if not has_tracking:
tracking_detail.result = "false"
tracking_detail.des = "提供的单号-快递公司关系疑似不匹配"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = url
tracking_detail.snapshot = snapshot
else:
item_length = soup.find_all(
"dd", attrs={'class': 'post_message'})
if item_length.__len__() > 0:
tracking_detail.result = "true"
tracking_detail.des = "巡检正常"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = url
tracking_detail.snapshot = snapshot
else:
tracking_detail.result = "false"
tracking_detail.des = "没有查询物流信息"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = url
tracking_detail.snapshot = snapshot
tracking_dao.update(tracking_detail)
except Exception as e:
logger.error(e)
tracking_detail.result = "false"
tracking_detail.des = "检测疑似异常，建议手动验证！"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = url
tracking_detail.snapshot = ""
tracking_dao.update(tracking_detail)
finally:
driver.quit()
else:
logger.info("单号任务没有需要检索的单号，任务id：%s，单号状态: %s", task_id, status)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
ims_api.done_tracking(task_id)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
def monitor(task_id, status):
ims_api = ImsApi()
tracking_dao = TrackingDetailDao()
status_dict = {'0': '查询中', '1': '查询不到', '2': '运输途中', '3': '到达待取', '4': '成功签收', '5': '运输过久',
'6': '投递失败', '7': '可能异常'}
normal_status_dict = {'0': '查询中', '1': '查询不到', '2': '运输途中', '3': '到达待取', '4': '成功签收', '5': '运输过久'}
tracking_details = tracking_dao.get_by_task(task_id, status)
if tracking_details.__len__() > 0:
try:
driver = WebDriver.get_chrome()
driver.get("https://www.trackingmore.com/login-cn.html")
driver.find_element_by_id("email").send_keys("*****@*****.**")
driver.find_element_by_id("password").send_keys("0418YXYwlx")
driver.find_element_by_id("login_test").click()
time.sleep(5)
for tracking_detail in tracking_details:
if gl.get_value('TRACKING_STATUS'):
pass
else:
logger.info("快递单任务已停止，任务id：%s", task_id)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
ims_api.done_tracking(task_id)
return
tracking_detail.start_time = datetime.datetime.now()
tracking_detail.status = "done"
logger.info("准备检查单号:%s ", tracking_detail.tracking_num)
try:
driver.get(
"https://my.51tracking.com/numbers.php?lang=cn&keywordType=trackNumber&p=1&searchnumber="
+ tracking_detail.tracking_num)
driver.maximize_window()
time.sleep(3)
# driver.find_element_by_class_name("show_lastEvent").click()
driver.find_element_by_id('trackItem_0').click()
time.sleep(1)
snapshot = SnapshotService.snapshot_tracking(driver, tracking_detail)
url = "https://my.51tracking.com/data/data-numbers.php?lang=cn&action=get_my_number" \
"&source=2&where=lang%3Dcn%26p%3D1%26keywordType%3DtrackNumber%26searchnumber%3D" \
+ tracking_detail.tracking_num + "&page=1"
driver.get(url)
json_data = driver.find_element_by_tag_name("body").text
json_obj = json.loads(str(json_data))
status = json_obj['data'][0]['track_status']
tracking_detail.des = status_dict[status]
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = ""
tracking_detail.snapshot = snapshot
if status in normal_status_dict:
logger.info("单号巡检状态:%s", status)
tracking_detail.result = "true"
else:
tracking_detail.result = "false"
tracking_dao.update(tracking_detail)
except Exception as e:
logger.error(e)
tracking_detail.result = "false"
tracking_detail.des = "检测疑似异常，建议手动验证！"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = ""
tracking_detail.snapshot = ""
tracking_dao.update(tracking_detail)
time.sleep(600)
except Exception as e:
logger.error(e)
tracking_detail.result = "false"
tracking_detail.des = "检测疑似异常，建议手动验证！"
tracking_detail.end_time = datetime.datetime.now()
tracking_detail.url = ""
tracking_detail.snapshot = ""
tracking_dao.update(tracking_detail)
finally:
driver.quit()
else:
logger.info("单号任务没有需要检索的单号，任务id：%s，单号状态: %s", task_id, status)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
ims_api.done_tracking(task_id)
gl.set_value('STATUS', False)
gl.set_value('TRACKING_STATUS', False)
def monitor_website(weburl, batch_num):
# 內容监控
keyword_dao = KeywordDao()
keywords = keyword_dao.get_all()
monitor_weburl_dao = MonitorWeburlDao()
monitor_weburl = MonitorUrl()
monitor_weburl.website_name = weburl.website_name
monitor_weburl.domain_name = weburl.domain_name
monitor_weburl.merchant_name = weburl.merchant_name
monitor_weburl.merchant_num = weburl.merchant_num
monitor_weburl.saler = weburl.saler
monitor_weburl.url = weburl.url
monitor_weburl.batch_num = batch_num
monitor_weburl.title = weburl.title
driver = WebDriver.get_phantomjs()
try:
logger.info("monitor_url: %s", weburl.url)
if str(weburl.url).startswith("http"):
print()
else:
weburl.url = "http://" + weburl.url
logger.info("weburl.url: %s", weburl)
logger.info("weburl.url: %s", weburl.url)
driver.get(weburl.url)
snapshot = SnapshotService.snapshot_weburl(driver, batch_num,
weburl, '网站内容')
logger.info("snapshot: %s", snapshot)
monitor_weburl.outline = ''
monitor_weburl.is_normal = '正常'
monitor_weburl.level = '-'
monitor_weburl.snapshot = snapshot
monitor_weburl.kinds = '是否能打开'
logger.info("monitor_url: add %s", weburl.url)
source = driver.page_source
if source.__eq__('<html><head></head><body></body></html>'):
monitor_weburl.outline = '网页打开异常'
monitor_weburl.is_normal = '异常'
else:
print()
monitor_weburl_dao.add(monitor_weburl)
soup = BeautifulSoup(source, 'html.parser')
# 监测页面敏感词
for keyword in keywords:
index = soup.find(keyword.name)
if index is not None:
logger.info(
"senti url alert,there is [ %s] in the url page!",
str(keyword.name))
monitor_weburl.outline = '检测到敏感词:' + str(keyword.name)
monitor_weburl.is_normal = '异常'
monitor_weburl.level = '低'
monitor_weburl.snapshot = snapshot
monitor_weburl.kinds = '命中敏感词'
monitor_weburl_dao.add(monitor_weburl)
# 监测 非金融平台包含充值、提现、钱包功能
illegal_fun = soup.find("充值")
if illegal_fun is not None:
logger.info("senti url alert,there is [ %s] in the url page!",
str("充值"))
monitor_weburl.outline = '检测到包含充值、提现、钱包功能'
monitor_weburl.is_normal = '异常'
monitor_weburl.level = '低'
monitor_weburl.snapshot = snapshot
monitor_weburl.kinds = '非法功能'
monitor_weburl_dao.add(monitor_weburl)
# 监测 误导宣传
mislead1 = soup.find("融宝资金担保")
mislead2 = soup.find("融宝托管")
if mislead1 is not None or mislead2 is not None:
monitor_weburl.outline = '检测到误导宣传'
monitor_weburl.is_normal = '异常'
monitor_weburl.level = '中'
monitor_weburl.snapshot = snapshot
monitor_weburl.kinds = '误导宣传'
monitor_weburl_dao.add(monitor_weburl)
except Exception as e:
# ERROR No transaction is begun.
logger.error(e)
conn = DB_Session()
try:
logger.info("检测到误404 : %s", weburl.url)
monitor_weburl.outline = '检测到页面404'
monitor_weburl.is_normal = '异常'
monitor_weburl.level = '高'
snapshot = SnapshotService.simulation_404(weburl.url)
monitor_weburl.snapshot = snapshot
monitor_weburl.kinds = '死链接'
logger.info("monitor_url:Exception %s", weburl.url)
monitor_weburl_dao.add(monitor_weburl)
except Exception as e:
logger.info(e)
conn.rollback()
raise
finally:
conn.close()
finally:
driver.quit()
def monitor_website(website, batch_num):
monitor_website_dao = MonitorWebsiteDao
if len(website.domain_name) == 0:
logger.info("website_domain is None! merchant_name: %s ",
website.merchant_name)
monitor_website = MonitorWebsite()
monitor_website.website_name = website.website_name
monitor_website.merchant_name = website.merchant_name
monitor_website.merchant_num = website.merchant_num
monitor_website.domain_name = website.domain_name
monitor_website.saler = website.saler
monitor_website.batch_num = batch_num
monitor_website.kinds = "首页是否可打开"
monitor_website.level = '-'
monitor_website.access = '异常'
monitor_website.is_normal = '无法获取'
monitor_website.outline = '商户域名为空。'
monitor_website.level = '-'
monitor_website.pageview = '-'
monitor_website_dao.add(monitor_website)
return
else:
logger.info("website_domain is not None! merchant_name: %s ",
website.domain_name)
# 首页监控
driver = WebDriver.get_phantomjs()
service = TrafficService()
access = AccessibleService()
domain_names = str(website.domain_name)
domain_name_list = domain_names.split(",")
for domain_name in domain_name_list:
try:
logger.info("-------------------")
logger.info("check whether website available,domain_name : %s",
website.domain_name)
# 截图
monitor_website = MonitorWebsite()
monitor_website.website_name = website.website_name
monitor_website.merchant_name = website.merchant_name
monitor_website.merchant_num = website.merchant_num
monitor_website.saler = website.saler
monitor_website.domain_name = domain_name
monitor_website.batch_num = batch_num
monitor_website.kinds = "首页是否可打开"
monitor_website.level = '-'
monitor_website.snapshot = ""
logger.info("预留使用代理入口...")
# domain_name_rich, current_url = access.get_proxy_access_res(domain_name)
# if domain_name_rich is None:
# logger.info("不使用代理重试访问： %s", domain_name)
# domain_name_rich, current_url = access.get_access_res(domain_name)
# else:
# logger.info("使用代理可以访问: %s", domain_name_rich)
domain_name_rich, current_url = access.get_access_res(
domain_name)
logger.info("domain_name: %s", domain_name)
logger.info("domain_name_rich: %s", domain_name_rich)
logger.info("current_url: %s", current_url)
if domain_name_rich is not None:
logger.info("domain : %s", str(domain_name_rich))
monitor_website.access = '正常'
monitor_website.is_normal = '正常'
monitor_website.outline = '正常'
monitor_website.level = '-'
monitor_website.pageview = '-'
monitor_website.batch_num = batch_num
pageview = service.get_traffic(
domain_name=domain_name_rich)
monitor_website.pageview = pageview.reach_rank[0]
try:
driver.get(domain_name_rich)
title = driver.title
snapshot = SnapshotService.create_snapshot(
driver, batch_num, website, '网站')
monitor_website.snapshot = snapshot
if title == '没有找到站点' or title == '未备案提示':
monitor_website.access = '异常'
monitor_website.is_normal = '异常'
monitor_website.outline = title
monitor_website.level = '高'
monitor_website_dao.add(monitor_website)
else:
monitor_website_dao.add(monitor_website)
except Exception as e:
logger.info(e)
monitor_website.access = '异常'
monitor_website.is_normal = '异常'
monitor_website.outline = '首页访问检测到异常'
monitor_website.level = '高'
monitor_website.pageview = '-'
monitor_website.snapshot = SnapshotService.simulation_404(
domain_name)
monitor_website.batch_num = batch_num
monitor_website_dao.add(monitor_website)
else:
monitor_website.access = '异常'
monitor_website.is_normal = '异常'
monitor_website.outline = '首页访问检测到异常'
monitor_website.level = '高'
monitor_website.pageview = '-'
monitor_website.batch_num = batch_num
if current_url is None:
logger.info("snapshot 404")
monitor_website.snapshot = SnapshotService.simulation_404(
domain_name)
else:
chrome_driver = WebDriver.get_chrome()
try:
chrome_driver.get(current_url)
snapshot = SnapshotService.create_snapshot(
chrome_driver, batch_num, website, '网站')
monitor_website.snapshot = snapshot
except Exception as e:
logger.error(e)
index = str(e).find("timeout")
if index != -1:
logger.info("访问超时")
monitor_website.outline = '访问超时'
monitor_website.snapshot = SnapshotService.simulation_404(
current_url)
else:
monitor_website.outline = str(e)
monitor_website.snapshot = SnapshotService.simulation_404(
current_url)
monitor_website_dao.add(monitor_website)
return None, None
finally:
chrome_driver.quit()
logger.info("website is not available : %s return!",
domain_name)
monitor_website_dao.add(monitor_website)
return
except Exception as e:
logger.info(e)
monitor_website.access = '异常'
monitor_website.is_normal = '异常'
monitor_website.outline = '巡检系统异常，建议手动重试!'
monitor_website.level = '高'
monitor_website_dao.add(monitor_website)
finally:
driver.quit()
