Request

Request 部分源码:

# 部分代码
class Request(object_ref):

    def __init__(self, url, callback=None, method='GET', headers=None, body=None, 
                 cookies=None, meta=None, encoding='utf-8', priority=0,
                 dont_filter=False, errback=None):

        self._encoding = encoding  # this one has to be set first
        self.method = str(method).upper()
        self._set_url(url)
        self._set_body(body)
        assert isinstance(priority, int), "Request priority not an integer: %r" % priority
        self.priority = priority

        assert callback or not errback, "Cannot use errback without a callback"
        self.callback = callback
        self.errback = errback

        self.cookies = cookies or {}
        self.headers = Headers(headers or {}, encoding=encoding)
        self.dont_filter = dont_filter

        self._meta = dict(meta) if meta else None

    @property
    def meta(self):
        if self._meta is None:
            self._meta = {}
        return self._meta

 其中,比较常用的参数:

url: 就是需要请求,并进行下一步处理的url

callback: 指定该请求返回的Response,由那个函数来处理。

method: 请求一般不需要指定,默认GET方法,可设置为"GET", "POST", "PUT"等,且保证字符串大写

headers: 请求时,包含的头文件。一般不需要。内容一般如下:
        # 自己写过爬虫的肯定知道
        Host: media.readthedocs.org
        User-Agent: Mozilla/5.0 (Windows NT 6.2; WOW64; rv:33.0) Gecko/20100101 Firefox/33.0
        Accept: text/css,*/*;q=0.1
        Accept-Language: zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3
        Accept-Encoding: gzip, deflate
        Referer: http://scrapy-chs.readthedocs.org/zh_CN/0.24/
        Cookie: _ga=GA1.2.1612165614.1415584110;
        Connection: keep-alive
        If-Modified-Since: Mon, 25 Aug 2014 21:59:35 GMT
        Cache-Control: max-age=0

meta: 比较常用,在不同的请求之间传递数据使用的。字典dict型

        request_with_cookies = Request(
            url="http://www.example.com",
            cookies={'currency': 'USD', 'country': 'UY'},
            meta={'dont_merge_cookies': True}
        )

encoding: 使用默认的 'utf-8' 就行。

dont_filter: 表明该请求不由调度器过滤。这是当你想使用多次执行相同的请求,忽略重复的过滤器。默认为False。

errback: 指定错误处理函数

Response

# 部分代码
class Response(object_ref):
    def __init__(self, url, status=200, headers=None, body='', flags=None, request=None):
        self.headers = Headers(headers or {})
        self.status = int(status)
        self._set_body(body)
        self._set_url(url)
        self.request = request
        self.flags = [] if flags is None else list(flags)

    @property
    def meta(self):
        try:
            return self.request.meta
        except AttributeError:
            raise AttributeError("Response.meta not available, this response " \
                "is not tied to any request")

大部分参数和上面的差不多:

status: 响应码
_set_body(body): 响应体
_set_url(url):响应url
self.request = request

发送POST请求

  • 可以使用 yield scrapy.FormRequest(url, formdata, callback)方法发送POST请求。

  • 如果希望程序执行一开始就发送POST请求,可以重写Spider类的start_requests(self) 方法,并且不再调用start_urls里的url。

class mySpider(scrapy.Spider):
    # start_urls = ["http://www.example.com/"]

    def start_requests(self):
        url = 'http://www.renren.com/PLogin.do'

        # FormRequest 是Scrapy发送POST请求的方法
        yield scrapy.FormRequest(
            url = url,
            formdata = {"email" : "mr_mao_hacker@163.com", "password" : "axxxxxxxe"},
            callback = self.parse_page
        )
    def parse_page(self, response):
        # do something

模拟登陆

使用FormRequest.from_response()方法模拟用户登录

通常网站通过 实现对某些表单字段(如数据或是登录界面中的认证令牌等)的预填充。

使用Scrapy抓取网页时,如果想要预填充或重写像用户名、用户密码这些表单字段, 可以使用 FormRequest.from_response() 方法实现。

renren.py

# -*- coding: utf-8 -*-
import scrapy


#根据cookie进行登录,实在没办法了,可以用这种方法模拟登录,麻烦一点,成功率100%
class RenrenSpider(scrapy.Spider):
    name = "renren"
    allowed_domains = ["renren.com"]
    start_urls = (
        # 'http://www.renren.com/xxxxx',
        'http://www.renren.com/11111',
        # 'http://www.renren.com/xx',
    )

    # 帐号登录后的cookie值
    cookies = {
        "anonymid": "ixrna3fysufnwv",
        "_r01_": "1",
        "ap": "327550029",
        "JSESSIONID": "abciwg61A_RvtaRS3GjOv",
        "depovince": "GW",
        "springskin": "set",
        "jebe_key": "f6fb270b-d06d-42e6-8b53-e67c3156aa7e%7Cc13c37f53bca9e1e7132d4b58ce00fa3%7C1484060607478%7C1%7C1486198628950",
        "jebe_key": "f6fb270b-d06d-42e6-8b53-e67c3156aa7e%7Cc13c37f53bca9e1e7132d4b58ce00fa3%7C1484060607478%7C1%7C1486198619601",
        "ver": "7.0",
        "XNESSESSIONID": "e703b11f8809",
        "jebecookies": "98c7c881-779f-4da8-a57c-7464175cd469|||||",
        "ick_login": "4b4a254a-9f25-4d4a-b686-a41fda73e173",
        "_de": "BF09EE3A28DED52E6B65F6A4705D973F1383380866D39FF5",
        "p": "ea5541736f993365a23d04c0946c10e29",
        "first_login_flag": "1",
        "ln_uact": "mr_mao_hacker@163.com",
        "ln_hurl": "http://hdn.xnimg.cn/photos/hdn521/20140529/1055/h_main_9A3Z_e0c300019f6a195a.jpg",
        "t": "691808127750a83d33704a565d8340ae9",
        "societyguester": "691808127750a83d33704a565d8340ae9",
        "id": "327550029",
        "xnsid": "f42b25cf",
        "loginfrom": "syshome"
    }

    #开始发送网站请求时调用该方法
    def start_requests(self):
        for url in self.start_urls:
            # yield scrapy.Request(url, callback = self.parse)
            # url = "http://www.renren.com/410043129/profile",登录进去后的页面
            yield scrapy.FormRequest(url, cookies=self.cookies, callback=self.parse_page)

    def parse_page(self, response):
        print("===========" + response.url)
        with open("deng.html", "wb") as filename:
            filename.write(response.body)

 

 

 

renren1.py

# -*- coding: utf-8 -*-
import scrapy


class Reren1Spider(scrapy.Spider):
    name = "reren1"
    allowed_domains = ["renren.com"]

    def start_requests(self):
        url = 'http://www.renren.com/PLogin.do'
        yield scrapy.FormRequest(
            url=url,
            formdata={"email": "mr_mao_hacker@163.com", "password": "alarmchime"},
            callback=self.parse_page)

    def parse_page(self, response):
        #登录后将登录页面写入到文件中
        print(response.body)
        with open("mao2.html", "wb") as filename:
            filename.write(response.body)

 

 

 

renren2.py

# -*- coding: utf-8 -*-
import scrapy

# 正统模拟登录方法:
# 首先发送登录页面的get请求,获取到页面里的登录必须的参数,比如说zhihu的 _xsrf
# 然后和账户密码一起post到服务器,登录成功

class Renren2Spider(scrapy.Spider):
    name = 'renren2'
    allowed_domains = ['renren.com']
    start_urls = ["http://www.renren.com/PLogin.do",]

    def parse(self, response):
        #验证登录是否成功
        yield scrapy.FormRequest.from_response(
            response,
            formdata={"email" : "mr_mao_hacker@163.com", "password" : "alarmchime"},#, "_xsrf" = _xsrf},
            callback=self.parse_page
        )


    def parse_page(self,response):
        #登录成功后,点击进入好友的页面
        url="http://www.renren.com/422167102/profile"
        yield scrapy.Request(url,callback=self.parse_newpage)


    def parse_newpage(self,response):
        with open("xiao.html", "wb") as filename:
            filename.write(response.body)