| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596 |
- # -*- coding: utf-8 -*-
- """
- -------------------------------------------------
- File Name: WebRequest
- Description : Network Requests Class
- Author : J_hao
- date: 2017/7/31
- -------------------------------------------------
- Change Activity:
- 2017/7/31:
- -------------------------------------------------
- """
- __author__ = 'J_hao'
- from requests.models import Response
- from lxml import etree
- import requests
- import random
- import time
- from handler.logHandler import LogHandler
- requests.packages.urllib3.disable_warnings()
- class WebRequest(object):
- name = "web_request"
- def __init__(self, *args, **kwargs):
- self.log = LogHandler(self.name, file=False)
- self.response = Response()
- @property
- def user_agent(self):
- """
- return an User-Agent at random
- :return:
- """
- ua_list = [
- 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101',
- 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122',
- 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71',
- 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95',
- 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71',
- 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)',
- 'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
- 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0',
- ]
- return random.choice(ua_list)
- @property
- def header(self):
- """
- basic header
- :return:
- """
- return {'User-Agent': self.user_agent,
- 'Accept': '*/*',
- 'Connection': 'keep-alive',
- 'Accept-Language': 'zh-CN,zh;q=0.8'}
- def get(self, url, header=None, retry_time=5, retry_interval=5, timeout=10, *args, **kwargs):
- """
- get method
- :param url: target url
- :param header: headers
- :param retry_time: retry time
- :param retry_interval: retry interval
- :param timeout: network timeout
- :return:
- """
- headers = self.header
- if header and isinstance(header, dict):
- headers.update(header)
- while True:
- try:
- self.response = requests.get(url, headers=headers, timeout=timeout, *args, **kwargs)
- return self
- except Exception as e:
- self.log.error("requests: %s error: %s" % (url, str(e)))
- retry_time -= 1
- if retry_time <= 0:
- resp = Response()
- resp.status_code = 200
- return self
- self.log.info("retry %s second after" % retry_interval)
- time.sleep(retry_interval)
- @property
- def tree(self):
- return etree.HTML(self.response.content)
- @property
- def text(self):
- return self.response.text
|