python爬蟲學習筆記 4.7 （Request/Response）

python爬蟲學習筆記 4.7 （Request/Response）

Request

Request 部分源碼：

# 部分代碼
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，比較常用的參數：

url: 就是需要請求，並進行下一步處理的url

callback: 指定該請求返回的Response，由那個函數來處理。

method: 請求一般不需要指定，默認GET方法，可設置爲"GET", "POST", "PUT"等，且保證字符串大寫

headers: 請求時，包含的頭文件。一般不需要。內容一般如下：
        # 自己寫過爬蟲的肯定知道
        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: 比較常用，在不同的請求之間傳遞數據使用的。字典dict型

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

encoding: 使用默認的 'utf-8' 就行。

dont_filter: 表明該請求不由調度器過濾。這是當你想使用多次執行相同的請求,忽略重複的過濾器。默認爲False。

errback: 指定錯誤處理函數

Response

部分代碼

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")

大部分參數和上面的差不多：

status: 響應碼
_set_body(body)： 響應體
_set_url(url)：響應url
self.request = request

發送POST請求

• 可以使用 yield scrapy.FormRequest(url, formdata, callback)方法發送POST請求。

• 如果希望程序執行一開始就發送POST請求，可以重寫Spider類的start_requests(self) 方法，並且不再調用start_urls裏的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發送POST請求的方法
        yield scrapy.FormRequest(
            url = url,
            formdata = {"email" : "[email protected]", "password" : "axxxxxxxe"},
            callback = self.parse_page
        )
    def parse_page(self, response):
        # do something

模擬登陸

使用FormRequest.from_response()方法模擬用戶登錄

通常網站通過 實現對某些表單字段（如數據或是登錄界面中的認證令牌等）的預填充。

使用Scrapy抓取網頁時，如果想要預填充或重寫像用戶名、用戶密碼這些表單字段， 可以使用 FormRequest.from_response() 方法實現。

下面是使用這種方法的爬蟲例子:

import scrapy

class LoginSpider(scrapy.Spider):
    name = 'example.com'
    start_urls = ['http://www.example.com/users/login.php']

    def parse(self, response):
        return scrapy.FormRequest.from_response(
            response,
            formdata={'username': 'john', 'password': 'secret'},
            callback=self.after_login
        )

    def after_login(self, response):
        # check login succeed before going on
        if "authentication failed" in response.body:
            self.log("Login failed", level=log.ERROR)
            return

        # continue scraping with authenticated session...

知乎爬蟲案例參考：

zhihuSpider.py爬蟲代碼

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from scrapy.spiders import CrawlSpider, Rule
from scrapy.selector import Selector
from scrapy.linkextractors import LinkExtractor
from scrapy import Request, FormRequest
from zhihu.items import ZhihuItem

class ZhihuSipder(CrawlSpider) :
    name = "zhihu"
    allowed_domains = ["www.zhihu.com"]
    start_urls = [
        "http://www.zhihu.com"
    ]
    rules = (
        Rule(LinkExtractor(allow = ('/question/\d+#.*?', )), callback = 'parse_page', follow = True),
        Rule(LinkExtractor(allow = ('/question/\d+', )), callback = 'parse_page', follow = True),
    )

    headers = {
        "Accept": "*/*",
        "Accept-Language": "en-US,en;q=0.8,zh-TW;q=0.6,zh;q=0.4",
        "Connection": "keep-alive",
        "Content-Type":" application/x-www-form-urlencoded; charset=UTF-8",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2125.111 Safari/537.36",
        "Referer": "http://www.zhihu.com/"
    }

    #重寫了爬蟲類的方法, 實現了自定義請求, 運行成功後會調用callback回調函數
    def start_requests(self):
        return [Request("https://www.zhihu.com/login", meta = {'cookiejar' : 1}, callback = self.post_login)]

    def post_login(self, response):
        print 'Preparing login'
        #下面這句話用於抓取請求網頁後返回網頁中的_xsrf字段的文字, 用於成功提交表單
        xsrf = response.xpath('//input[@name="_xsrf"]/@value').extract()[0]
        print xsrf
        #FormRequeset.from_response是Scrapy提供的一個函數, 用於post表單
        #登陸成功後, 會調用after_login回調函數
        return [FormRequest.from_response(response,   #"http://www.zhihu.com/login",
                            meta = {'cookiejar' : response.meta['cookiejar']},
                            headers = self.headers,  #注意此處的headers
                            formdata = {
                            '_xsrf': xsrf,
                            'email': '[email protected]',
                            'password': '123456'
                            },
                            callback = self.after_login,
                            dont_filter = True
                            )]

    def after_login(self, response) :
        for url in self.start_urls :
            yield self.make_requests_from_url(url)

    def parse_page(self, response):
        problem = Selector(response)
        item = ZhihuItem()
        item['url'] = response.url
        item['name'] = problem.xpath('//span[@class="name"]/text()').extract()
        print item['name']
        item['title'] = problem.xpath('//h2[@class="zm-item-title zm-editable-content"]/text()').extract()
        item['description'] = problem.xpath('//div[@class="zm-editable-content"]/text()').extract()
        item['answer']= problem.xpath('//div[@class=" zm-editable-content clearfix"]/text()').extract()
        return item

Item類設置

from scrapy.item import Item, Field

class ZhihuItem(Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    url = Field()  #保存抓取問題的url
    title = Field()  #抓取問題的標題
    description = Field()  #抓取問題的描述
    answer = Field()  #抓取問題的答案
    name = Field()  #個人用戶的名稱

setting.py 設置抓取間隔

BOT_NAME = 'zhihu'

SPIDER_MODULES = ['zhihu.spiders']
NEWSPIDER_MODULE = 'zhihu.spiders'
DOWNLOAD_DELAY = 0.25   #設置下載間隔爲250ms