【python爬虫】设计自己的爬虫 1. request封装
通过requests.session().request 封装request方法
考虑到请求HTTP/2.0
同时封装httpx 来处理HTTP/2.0的请求
封装requests
# 遇到请求失败的情况时 重新请求，请求5次等待2s
@retry(stop_max_attempt_number=5, retry_on_result=lambda re_data: re_data is None, wait_fixed=2000)def requests_request(self, method, url, params=None, data=None, json=None, headers=None, files=None, verify=False,cert=None, timeout=None, proxies=None, proxy=None, **kwargs):# 对异常进行捕获try:"""封装request请求，将请求方法、请求地址，请求参数、请求头等信息入参。注 ：verify: True/False，默认为True，认证SSL证书开关；cert: 本地SSL证书。如果不需要ssl认证，可将这两个入参去掉使用session管理器requests.session(): 维持会话,跨请求的时候保存参数 """# 处理代理proxies = Noneif proxy:proxies = {'http://': 'http://' + proxy,'https://': 'https://' + proxy,}# 使用requests.session().request 请求re_data = requests.session().request(method, url, params=params, data=data, json=json, headers=headers,files=files, cert=cert, timeout=timeout, verify=verify,proxies=proxies, **kwargs)# 异常处理 报错显示具体信息except Exception as e:re_data = None# 打印异常print("请求失败：{0}".format(e))logger.error("Error occurred: %s", str(e), exc_info=True)# 重新抛出异常，触发 retry 机制raise e# 返回响应结果return re_data
封装httpx
@retry(stop_max_attempt_number=5, retry_on_result=lambda re_data: re_data is None, wait_fixed=2000)def httpx_request(self, method, url, is_http2=False, content=None, data=None, files=None, json=None, params=None,headers=None, cookies=None, timeout=None, extensions=None, proxy=None, **kwargs):# 对异常进行捕获try:"""使用client method.upper() 请求方法都转为大写"""# 处理代理proxies = Noneif proxy:proxies = {'http://': 'http://' + proxy,'https://': 'https://' + proxy,}re_data = httpx.Client(http2=is_http2, proxies=proxies).request(method.upper(), url, content=content,data=data, files=files, json=json,params=params, headers=headers,cookies=cookies, timeout=timeout,extensions=extensions, **kwargs)# 异常处理 报错显示具体信息except Exception as e:re_data = None# 打印异常print("请求失败：{0}".format(e))logger.error("Error occurred: %s", str(e), exc_info=True)# 重新抛出异常，触发 retry 机制raise e# 返回响应结果return re_data将两个请求封装在一个方法里
@retry(stop_max_attempt_number=5, retry_on_result=lambda re_data: re_data is None, wait_fixed=2000)def request(self, method, url, is_http2=False, params=None, data=None, json=None, headers=None, files=None,verify=False, cert=None, timeout=None, proxies=None, content=None, cookies=None, extensions=None,**kwargs):try:if is_http2:re_data = self.httpx_request(method=method.upper(), url=url, is_http2=is_http2, content=content,data=data, files=files, json=json, params=params, headers=headers,cookies=cookies, timeout=timeout, extensions=extensions, **kwargs)else:re_data = self.requests_request(method=method, url=url, params=params, data=data, json=json,headers=headers, files=files, cert=cert, timeout=timeout, verify=verify,proxies=proxies, **kwargs)# 异常处理 报错显示具体信息except Exception as e:re_data = None# 打印异常print("请求失败：{0}".format(e))logger.error("Error occurred: %s", str(e), exc_info=True)# 重新抛出异常，触发 retry 机制raise e# 返回响应结果return re_data通过is_http2来区分
测试代码如下
if __name__ == '__main__':# request_requests 使用requests请求request_data = request_main.requests_request("get", 'https://spa16.scrape.center/')if request_data:print(request_data.text)print(request_data.status_code)# httpx 请求HTTP/2.0# response = re.httpx_request('GET', 'https://spa16.scrape.center/', True)# httpx 一般请求# headers = {'User-Agent': 'my-app/0.0.1'}# response = re.httpx_request('get', 'https://www.httpbin.org/get',params={'name': 'germey'})# print(response.text)# print(response.status_code)print(datetime.datetime.now())