grequests模块的使用

使用场景：1) 爬虫设置ip代理池时验证ip是否有效 2）进行压测时，进行批量请求等等场景
grequests 利用 requests和gevent库，做了一个简单封装，使用起来非常方便。
grequests.map(requests, stream=False, size=None, exception_handler=None, gtimeout=None)
另外，由于grequests底层使用的是requests，因此它支持
GET，OPTIONS， HEAD， POST， PUT， DELETE 等各种http method
所以以下的任务请求都是支持的
grequests.post(url, json={“name”:“zhangsan”})
grequests.delete(url)
代码如下:

import grequests

urls = [
    'http://www.baidu.com',
    'http://www.qq.com',
    'http://www.163.com',
    'http://www.zhihu.com',
    'http://www.toutiao.com',
    'http://www.douban.com'
]
rs = (grequests.get(u) for u in urls)
print(grequests.map(rs))   # [<Response [200]>, None, <Response [200]>, None, None, <Response [418]>]
def exception_handler(request, exception):
    print("Request failed")
reqs = [
    grequests.get('http://httpbin.org/delay/1', timeout=0.001),
    grequests.get('http://fakedomain/'),
    grequests.get('http://httpbin.org/status/500')
]
print(grequests.map(reqs, exception_handler=exception_handler))

实际操作中，也可以自定义返回的结果
修改grequests源码文件:
例如:
新增extract_item() 函数合修改map()函数

def extract_item(request):
    """
    提取request的内容
    :param request:
    :return:
    """
    item = dict()
    item["url"] = request.url
    item["text"] = request.response.text or ""
    item["status_code"] = request.response.status_code or 0
    return item

def map(requests, stream=False, size=None, exception_handler=None, gtimeout=None):
    """Concurrently converts a list of Requests to Responses.

    :param requests: a collection of Request objects.
    :param stream: If True, the content will not be downloaded immediately.
    :param size: Specifies the number of requests to make at a time. If None, no throttling occurs.
    :param exception_handler: Callback function, called when exception occured. Params: Request, Exception
    :param gtimeout: Gevent joinall timeout in seconds. (Note: unrelated to requests timeout)
    """
    requests = list(requests)
    pool = Pool(size) if size else None
    jobs = [send(r, pool, stream=stream) for r in requests]
    gevent.joinall(jobs, timeout=gtimeout)
    ret = []
    for request in requests:

        if request.response is not None:
            ret.append(extract_item(request))
        elif exception_handler and hasattr(request, 'exception'):
            ret.append(exception_handler(request, request.exception))
        else:
            ret.append(None)

    yield ret

可以直接调用:

import grequests

urls = [
    'http://www.baidu.com',
    'http://www.qq.com',
    'http://www.163.com',
    'http://www.zhihu.com',
    'http://www.toutiao.com',
    'http://www.douban.com'
]
rs = (grequests.get(u) for u in urls)
response_list = grequests.map(rs, gtimeout=10)
for response in next(response_list):
    print(response)

支持事件钩子
def print_url(r, *args, **kwargs):
print(r.url)

url = “http://www.baidu.com”
res = requests.get(url, hooks={“response”: print_url})
tasks = []
req = grequests.get(url, callback=print_url)
tasks.append(req)
ress = grequests.map(tasks)
print(ress)