Scrapy爬虫笔记 - 爬取知乎

cookie是一种本地存储机制，cookie是存储在本地的

session其实就是将用户信息用户名、密码等）加密成一串字符串，返回给浏览器，以后浏览器每次请求都带着这个sessionId

状态码一般是服务器自己定义，也可以框架定义，也可以自己定义

F12 NetWork 下可以看到每个请求的状态码

301永久性重定向，比如更换了 域名，但又希望原域名可以请求的到

302临时性重定向，比如未登录状态下点击个人中心，会重定向到登陆页面

404一般是url非法，当然这种情况也可以返回200的空页面，但是这样不太好，因为404可以被过滤掉

500一般是服务器中某个函数出错了，但是又没有捕获异常，一般开发框架会处理

503的状况一般暂停爬虫，一般只爬取200，也不爬404

如果要爬知乎，先登录

可以通过输入错误的用户名密码，在network中找到posturl和post参数

requests.get() 默认加的header是python2或者python3，直接请求会报500

所以requests时需要加header

agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
header = {
    "HOST":"www.zhihu.com",
    "Referer": "https://www.zhizhu.com",
    'User-Agent': agent
}

response = session.get("https://www.zhihu.com", headers=header)

模拟登陆时，不是直接用requests，而且用requests的session，session代表某一次连接，这样就不需要每次requests.get时都建立连接，效率是更高的

session = requests.session()

response = session.get("https://www.zhihu.com", headers=header)

后面所以的requests都可以换成session

session.cookies没有save()方法，可以用session.cookies = cookielib.LWPCookieJar()实例化出来的cookies可以有save()

知乎模拟登陆代码（未使用scrapy）

# -*- coding: utf-8 -*-
__author__ = 'bobby'

import requests
try:
    import cookielib
except:
    import http.cookiejar as cookielib

import re

session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename="cookies.txt")
try:
    session.cookies.load(ignore_discard=True)
except:
    print ("cookie未能加载")

agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
header = {
    "HOST":"www.zhihu.com",
    "Referer": "https://www.zhizhu.com",
    'User-Agent': agent
}

def is_login():
    #通过个人中心页面返回状态码来判断是否为登录状态
    inbox_url = "https://www.zhihu.com/question/56250357/answer/148534773"
    response = session.get(inbox_url, headers=header, allow_redirects=False)
    if response.status_code != 200:
        return False
    else:
        return True

def get_xsrf():
    #获取xsrf code
    response = session.get("https://www.zhihu.com", headers=header)
    match_obj = re.match('.*name="_xsrf" value="(.*?)"', response.text)
    if match_obj:
        return (match_obj.group(1))
    else:
        return ""

def get_index():
    response = session.get("https://www.zhihu.com", headers=header)
    with open("index_page.html", "wb") as f:
        f.write(response.text.encode("utf-8"))
    print ("ok")

def get_captcha():
    import time
    t = str(int(time.time()*1000))
    captcha_url = "https://www.zhihu.com/captcha.gif?r={0}&type=login".format(t)
    t = session.get(captcha_url, headers=header)
    with open("captcha.jpg","wb") as f:
        f.write(t.content)
        f.close()

    from PIL import Image
    try:
        im = Image.open('captcha.jpg')
        im.show()
        im.close()
    except:
        pass

    captcha = input("输入验证码\n>")
    return captcha

def zhihu_login(account, password):
    #知乎登录
    if re.match("^1\d{10}",account):
        print ("手机号码登录")
        post_url = "https://www.zhihu.com/login/phone_num"
        post_data = {
            "_xsrf": get_xsrf(),
            "phone_num": account,
            "password": password,
            "captcha":get_captcha()
        }
    else:
        if "@" in account:
            #判断用户名是否为邮箱
            print("邮箱方式登录")
            post_url = "https://www.zhihu.com/login/email"
            post_data = {
                "_xsrf": get_xsrf(),
                "email": account,
                "password": password
            }

    response_text = session.post(post_url, data=post_data, headers=header)
    session.cookies.save()

zhihu_login("", "admin123")
# get_index()
is_login()

# get_captcha()

zhihu_login_requests.py

scrapy的spider的入口是start_requests
所以需要重写start_requests

异步UI
def start_requests(self):
return [scrapy.Request('https://www.zhihu.com/#signin', headers=self.headers, callback=self.login)]

callback不加括号是因为传递的是这个函数的对象，它是会被调用的，如果你现在加了括号，那就代表现在就调用它，它就会返回这个函数的值给你，，所以只需要传递函数名过去就好了

通过robot.txt会判断哪些页面会过滤掉

ROBOTSTXT_OBEY = False 不遵守ROBOTS协议

正则表达式默认只匹配一行
加re.DOTALL可以匹配全文

Scrapy shell 如何添加 User_Agent

scrapy shell -s USER_AGENT="Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/60.0" https://blog.csdn.net/weixin_42471384/article/details/81556531

# -*- coding: utf-8 -*-
import re
import json
import datetime

try:
    import urlparse as parse
except:
    from urllib import parse

import scrapy
from scrapy.loader import ItemLoader
from items import ZhihuQuestionItem, ZhihuAnswerItem

class ZhihuSpider(scrapy.Spider):
    name = "zhihu"
    allowed_domains = ["www.zhihu.com"]
    start_urls = ['https://www.zhihu.com/']

    #question的第一页answer的请求url
    start_answer_url = "https://www.zhihu.com/api/v4/questions/{0}/answers?sort_by=default&include=data%5B%2A%5D.is_normal%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccollapsed_counts%2Creviewing_comments_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Cmark_infos%2Ccreated_time%2Cupdated_time%2Crelationship.is_author%2Cvoting%2Cis_thanked%2Cis_nothelp%2Cupvoted_followees%3Bdata%5B%2A%5D.author.is_blocking%2Cis_blocked%2Cis_followed%2Cvoteup_count%2Cmessage_thread_token%2Cbadge%5B%3F%28type%3Dbest_answerer%29%5D.topics&limit={1}&offset={2}"

    headers = {
        "HOST": "www.zhihu.com",
        "Referer": "https://www.zhizhu.com",
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
    }

    custom_settings = {
        "COOKIES_ENABLED": True
    }

    def parse(self, response):
        """
        提取出html页面中的所有url 并跟踪这些url进行一步爬取
        如果提取的url中格式为 /question/xxx 就下载之后直接进入解析函数
        """
        all_urls = response.css("a::attr(href)").extract()
        all_urls = [parse.urljoin(response.url, url) for url in all_urls]
        all_urls = filter(lambda x:True if x.startswith("https") else False, all_urls)
        for url in all_urls:
            match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*", url)
            if match_obj:
                #如果提取到question相关的页面则下载后交由提取函数进行提取
                request_url = match_obj.group(1)
                yield scrapy.Request(request_url, headers=self.headers, callback=self.parse_question)
            else:
                #如果不是question页面则直接进一步跟踪
                yield scrapy.Request(url, headers=self.headers, callback=self.parse)

    def parse_question(self, response):
        #处理question页面， 从页面中提取出具体的question item
        if "QuestionHeader-title" in response.text:
            #处理新版本
            match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*", response.url)
            if match_obj:
                question_id = int(match_obj.group(2))

            item_loader = ItemLoader(item=ZhihuQuestionItem(), response=response)
            item_loader.add_css("title", "h1.QuestionHeader-title::text")
            item_loader.add_css("content", ".QuestionHeader-detail")
            item_loader.add_value("url", response.url)
            item_loader.add_value("zhihu_id", question_id)
            item_loader.add_css("answer_num", ".List-headerText span::text")
            item_loader.add_css("comments_num", ".QuestionHeader-actions button::text")
            item_loader.add_css("watch_user_num", ".NumberBoard-value::text")
            item_loader.add_css("topics", ".QuestionHeader-topics .Popover div::text")

            question_item = item_loader.load_item()
        else:
            #处理老版本页面的item提取
            match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*", response.url)
            if match_obj:
                question_id = int(match_obj.group(2))

            item_loader = ItemLoader(item=ZhihuQuestionItem(), response=response)
            # item_loader.add_css("title", ".zh-question-title h2 a::text")
            item_loader.add_xpath("title", "//*[@id='zh-question-title']/h2/a/text()|//*[@id='zh-question-title']/h2/span/text()")
            item_loader.add_css("content", "#zh-question-detail")
            item_loader.add_value("url", response.url)
            item_loader.add_value("zhihu_id", question_id)
            item_loader.add_css("answer_num", "#zh-question-answer-num::text")
            item_loader.add_css("comments_num", "#zh-question-meta-wrap a[name='addcomment']::text")
            # item_loader.add_css("watch_user_num", "#zh-question-side-header-wrap::text")
            item_loader.add_xpath("watch_user_num", "//*[@id='zh-question-side-header-wrap']/text()|//*[@class='zh-question-followers-sidebar']/div/a/strong/text()")
            item_loader.add_css("topics", ".zm-tag-editor-labels a::text")

            question_item = item_loader.load_item()

        yield scrapy.Request(self.start_answer_url.format(question_id, 20, 0), headers=self.headers, callback=self.parse_answer)
        yield question_item

    def parse_answer(self, reponse):
        #处理question的answer
        ans_json = json.loads(reponse.text)
        is_end = ans_json["paging"]["is_end"]
        next_url = ans_json["paging"]["next"]

        #提取answer的具体字段
        for answer in ans_json["data"]:
            answer_item = ZhihuAnswerItem()
            answer_item["zhihu_id"] = answer["id"]
            answer_item["url"] = answer["url"]
            answer_item["question_id"] = answer["question"]["id"]
            answer_item["author_id"] = answer["author"]["id"] if "id" in answer["author"] else None
            answer_item["content"] = answer["content"] if "content" in answer else None
            answer_item["parise_num"] = answer["voteup_count"]
            answer_item["comments_num"] = answer["comment_count"]
            answer_item["create_time"] = answer["created_time"]
            answer_item["update_time"] = answer["updated_time"]
            answer_item["crawl_time"] = datetime.datetime.now()

            yield answer_item

        if not is_end:
            yield scrapy.Request(next_url, headers=self.headers, callback=self.parse_answer)

    def start_requests(self):
        return [scrapy.Request('https://www.zhihu.com/#signin', headers=self.headers, callback=self.login)]

    def login(self, response):
        response_text = response.text
        match_obj = re.match('.*name="_xsrf" value="(.*?)"', response_text, re.DOTALL)
        xsrf = ''
        if match_obj:
            xsrf = (match_obj.group(1))

        if xsrf:
            post_url = "https://www.zhihu.com/login/phone_num"
            post_data = {
                "_xsrf": xsrf,
                "phone_num": "",
                "password": "",
                "captcha": ""
            }

            import time
            t = str(int(time.time() * 1000))
            captcha_url = "https://www.zhihu.com/captcha.gif?r={0}&type=login".format(t)
            yield scrapy.Request(captcha_url, headers=self.headers, meta={"post_data":post_data}, callback=self.login_after_captcha)

    def login_after_captcha(self, response):
        with open("captcha.jpg", "wb") as f:
            f.write(response.body)
            f.close()

        from PIL import Image
        try:
            im = Image.open('captcha.jpg')
            im.show()
            im.close()
        except:
            pass

        captcha = input("输入验证码\n>")

        post_data = response.meta.get("post_data", {})
        post_url = "https://www.zhihu.com/login/phone_num"
        post_data["captcha"] = captcha
        return [scrapy.FormRequest(
            url=post_url,
            formdata=post_data,
            headers=self.headers,
            callback=self.check_login
        )]

    def check_login(self, response):
        #验证服务器的返回数据判断是否成功
        text_json = json.loads(response.text)
        if "msg" in text_json and text_json["msg"] == "登录成功":
            for url in self.start_urls:
                yield scrapy.Request(url, dont_filter=True, headers=self.headers)

zhihu.py

。。。。。。