Scrapy 抓取知乎的问题

摘要：从如何评价的话题下开始抓取问题，然后开始爬相关问题再循环对于每个问题抓取标题，关注人数，回答数等数据设置用户名和密码设置获取值获得验证码的地址准备下载验证码获取请求下载验证码打开验证码输入验证码请输入验证码输入账号和

从如何评价X的话题下开始抓取问题，然后开始爬相关问题再循环

对于每个问题抓取 标题，关注人数，回答数等数据

zhihuTopicSpider.py

# -*- coding: utf-8 -*-

import scrapy
import os
import time
import re
import json

from ..items import zhihuQuestionItem

# mode 1:tencent   2:free
mode = 2
proxy = "https://web-proxy.oa.com:8080" if mode == 1 else ""

# 设置 用户名和密码
email = "youremail"
password = "yourpassword"


class zhihu_topicSpider(scrapy.Spider):
    name = "zhihu_topicSpider"
    zhihu_url = "https://www.zhihu.com"
    login_url = "https://www.zhihu.com/login/email"
    topic = "https://www.zhihu.com/topic"
    domain = "https://www.zhihu.com"

    # 设置 Headers
    headers_dict = {
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
        "Accept-Language": "zh-CN,zh;q=0.8",
        "Connection": "keep-alive",
        "Host": "www.zhihu.com",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.109 Safari/537.36"
    }

    def start_requests(self):
        yield scrapy.Request(
            url=self.zhihu_url,
            headers=self.headers_dict,
            meta={
                "proxy": proxy,
                "cookiejar": 1
            },
            callback=self.request_captcha
        )

    def request_captcha(self, response):
        # 获取_xsrf值
        _xsrf = response.css("input[name="_xsrf"]::attr(value)").extract()[0]
        # 获得验证码的地址
        captcha_url = "http://www.zhihu.com/captcha.gif?r=" + str(time.time() * 1000)
        # 准备下载验证码
        # 获取请求
        yield scrapy.Request(
            url=captcha_url,
            headers=self.headers_dict,
            meta={
                "proxy": proxy,
                "cookiejar": response.meta["cookiejar"],
                "_xsrf": _xsrf
            },
            callback=self.download_captcha
        )

    def download_captcha(self, response):
        # 下载验证码
        with open("captcha.gif", "wb") as fp:
            fp.write(response.body)
        # 打开验证码
        os.system("open captcha.gif")
        # 输入验证码
        print "请输入验证码:
"
        captcha = raw_input()
        # 输入账号和密码
        yield scrapy.FormRequest(
            url=self.login_url,
            headers=self.headers_dict,
            formdata={
                "email": email,
                "password": password,
                "_xsrf": response.meta["_xsrf"],
                "remember_me": "true",
                "captcha": captcha
            },
            meta={
                "proxy": proxy,
                "cookiejar": response.meta["cookiejar"],
            },
            callback=self.request_zhihu
        )

    def request_zhihu(self, response):
        """
            现在已经登录,请求www.zhihu.com的页面
        """
        yield scrapy.Request(url=self.topic + "/19760570",
                             headers=self.headers_dict,
                             meta={
                                 "proxy": proxy,
                                 "cookiejar": response.meta["cookiejar"],
                             },
                             callback=self.get_topic_question,
                             dont_filter=True)

    def get_topic_question(self, response):
        # with open("topic.html", "wb") as fp:
        #     fp.write(response.body)
        # 获得话题下的question的url
        question_urls = response.css(".question_link[target=_blank]::attr(href)").extract()
        length = len(question_urls)
        k = -1
        j = 0
        temp = []
        for j in range(length/3):
            temp.append(question_urls[k+3])
            j+=1
            k+=3
        for url in temp:
            yield scrapy.Request(url = self.zhihu_url+url,
                    headers = self.headers_dict,
                    meta = {
                        "proxy": proxy,
                        "cookiejar": response.meta["cookiejar"],
                    },
                    callback = self.parse_question_data)

    def parse_question_data(self, response):
        item = zhihuQuestionItem()
        item["qid"] = re.search("d+",response.url).group()
        item["title"] = response.css(".zm-item-title::text").extract()[0].strip()
        item["answers_num"] = response.css("h3::attr(data-num)").extract()[0]
        question_nums = response.css(".zm-side-section-inner .zg-gray-normal strong::text").extract()
        item["followers_num"] = question_nums[0]
        item["visitsCount"] = question_nums[1]
        item["topic_views"] = question_nums[2]
        topic_tags = response.css(".zm-item-tag::text").extract()
        if len(topic_tags) >= 3:
            item["topic_tag0"] = topic_tags[0].strip()
            item["topic_tag1"] = topic_tags[1].strip()
            item["topic_tag2"] = topic_tags[2].strip()
        elif len(topic_tags) == 2:
            item["topic_tag0"] = topic_tags[0].strip()
            item["topic_tag1"] = topic_tags[1].strip()
            item["topic_tag2"] = "-"
        elif len(topic_tags) == 1:
            item["topic_tag0"] = topic_tags[0].strip()
            item["topic_tag1"] = "-"
            item["topic_tag2"] = "-"
        # print type(item["title"])
        question_links = response.css(".question_link::attr(href)").extract()
        yield item
        for url in question_links:
            yield scrapy.Request(url = self.zhihu_url+url,
                    headers = self.headers_dict,
                    meta = {
                        "proxy": proxy,
                        "cookiejar": response.meta["cookiejar"],
                    },
                    callback = self.parse_question_data)

pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don"t forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

# import json
import MySQLdb

# class JsonDumpPipeline(object):
#     def process_item(self, item, spider):
#         with open("d.json", "a") as fp:
#             fp.write(json.dumps(dict(item), ensure_ascii = False).encode("utf-8") + "
")



class MySQLPipeline(object):
    print "







"
    sql_questions = (
            "INSERT INTO questions("
            "qid, title, answers_num, followers_num, visitsCount, topic_views, topic_tag0, topic_tag1, topic_tag2) "
            "VALUES ("%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s")")
    count = 0

    def open_spider(self, spider):
        host = "localhost"
        user = "root"
        password = "wangqi"
        dbname = "zh"
        self.conn = MySQLdb.connect(host, user, password, dbname)
        self.cursor = self.conn.cursor()
        self.conn.set_character_set("utf8")
        self.cursor.execute("SET NAMES utf8;")
        self.cursor.execute("SET CHARACTER SET utf8;")
        self.cursor.execute("SET character_set_connection=utf8;")
        print "

MYSQL DB CURSOR INIT SUCCESS!!

"
        sql = (
            "CREATE TABLE IF NOT EXISTS questions ("
                "qid VARCHAR (100) NOT NULL,"
                "title varchar(100),"
                "answers_num INT(11),"
                "followers_num INT(11) NOT NULL,"
                "visitsCount INT(11),"
                "topic_views INT(11),"
                "topic_tag0 VARCHAR (600),"
                "topic_tag1 VARCHAR (600),"
                "topic_tag2 VARCHAR (600),"
                "PRIMARY KEY (qid)"
            ")")
        self.cursor.execute(sql)
        print "

TABLES ARE READY!

"

    def process_item(self, item, spider):
        sql = self.sql_questions % (item["qid"], item["title"], item["answers_num"],item["followers_num"],
                                item["visitsCount"], item["topic_views"], item["topic_tag0"], item["topic_tag1"], item["topic_tag2"])
        self.cursor.execute(sql)
        if self.count % 10 == 0:
            self.conn.commit()
        self.count += 1
        print item["qid"] + " DATA COLLECTED!"

items.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy
from scrapy import Field


class zhihuQuestionItem(scrapy.Item):
    qid = Field()
    title = Field()
    followers_num = Field()
    answers_num = Field()
    visitsCount = Field()
    topic_views = Field()
    topic_tag0 = Field()
    topic_tag1 = Field()
    topic_tag2 = Field()