def get_list(string):
info = {}
flag = 0
try:
headers = config.headers_index
content, status_code = Send_Request().send_request(
config.index_url, headers)
if status_code == 200:
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
id = result.xpath('//span[@class = "shouButton"]/@onclick')[0]
pattern = re.compile(".*QueryIndex\('','(.*?)'\).*")
match_id = re.findall(pattern, id)[0]
url = config.list_url.format(match_id)
#随机生成UA
a = random.randrange(1, 1001) # 1-1000中生成随机数
headers = config.headers
params = config.list_parmas.format(string)
theline = linecache.getline(r'user-agent.txt', a)
theline = theline.replace("\n", '')
headers["User-Agent"] = theline
result = requests.post(url, params, headers=headers)
status_code = result.status_code
s = chardet.detect(result.content)["encoding"]
if status_code == 200 and s == 'utf-8':
pattern = re.compile(u".*无查询结果.*|.*访问频繁.*|.*访问异常.*")
match = re.findall(pattern, result.content)
if len(match) == 0:
content = etree.HTML(
result.content,
parser=etree.HTMLParser(encoding='utf-8'))
list = content.xpath("//li")
for i, single in enumerate(list):
item = single.xpath(".//a/@href")[0]
url = config.host + item
info[i] = url
flag = 1
else:
flag = 100000003
else:
flag = 100000004
else:
flag = 10000004
except Exception, e:
logging.error("search error:%s" % e)
flag = 100000004
def get_deatail_info(self, detail_url, info):
dict = {
u"执行事项": "items",
u"裁定书文号": "rule_no",
u"证照种类": "cert_cate",
u"证照号码": "cert_code",
u"冻结期限自": "start_date",
u"冻结期限至": "end_date",
u"冻结期限": "period",
u"公示日期": "pub_date"
}
headers = config.headers
result, status_code = Send_Request().send_requests(detail_url, headers)
if status_code == 200:
data = result.xpath(result,
parser=etree.HTMLParser(encoding='utf-8'))
for key, value in dict:
content = deal_html_code.get_match_info(key, data)
info[value] = content
else:
logging.info("获取司法协助详情信息失败！")
