爬取知乎question时遇到了问题

经过前几天的学习，知乎爬虫的逻辑已经实现。代码如下

zhihu.py

# -*- 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,
        "DOWNLOAD_DELAY": 1.5,
    }

    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", ".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", ".QuestionHeaderActions button::text")
            item_loader.add_css("watch_user_num", ".NumberBoard-itemValue::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_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_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questiona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
            #用户匿名时id这个字段就为空
            answer_item["content"] = answer["content"] if "content" in answer else None
            #有些情况下cotent字段也为空
            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)
            #异步I/O，通过callback执行下一步


    def start_requests(self):
        from selenium import webdriver
        browser = webdriver.Chrome(executable_path="C:/Users/Fitz/Desktop/software/chromedriver.exe")

        browser.get("https://www.zhihu.com/signin")
        browser.find_element_by_css_selector(".SignFlow-accountInput.Input-wrapper Input").send_keys(
            "17756021040")
        browser.find_element_by_css_selector(".SignFlow-password Input").send_keys(
            "yinjun123456789")
        browser.find_element_by_css_selector(".Button.SignFlow-submitButton").click()

        import time
        time.sleep(10)
        Cookies = browser.get_cookies()
        print(Cookies)
        cookie_dict = {}
        import pickle
        for cookie in Cookies:
            # 写入文件
            f = open('C:/Users/Fitz/Desktop/scrapy/ArticleSpider/cookies/zhihu/' + cookie['name'] + '.zhihu', 'wb')
            pickle.dump(cookie, f)
            f.close()
            cookie_dict[cookie['name']] = cookie['value']
        browser.close()

        return [scrapy.Request(url=self.start_urls[0], dont_filter=True, cookies=cookie_dict, headers=self.headers)]

items.py

class ZhihuQuestionItem(scrapy.Item):
    #知乎的问题 item
    zhihu_id = scrapy.Field()
    topics = scrapy.Field()
    url = scrapy.Field()
    title = scrapy.Field()
    content = scrapy.Field()
    answer_num = scrapy.Field()
    comments_num = scrapy.Field()
    watch_user_num = scrapy.Field()
    click_num = scrapy.Field()
    crawl_time = scrapy.Field()

    def get_insert_sql(self):
        #插入知乎question表的sql语句
        insert_sql = """
            insert into zhihu_question(zhihu_id, topics, url, title, content, answer_num, comments_num,
              watch_user_num, click_num, crawl_time
              )
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
            ON DUPLICATE KEY UPDATE content=VALUES(content), answer_num=VALUES(answer_num), comments_num=VALUES(comments_num),
              watch_user_num=VALUES(watch_user_num), click_num=VALUES(click_num)
        """
        zhihu_id = self["zhihu_id"][0]
        topics = ",".join(self["topics"])
        url = self["url"][0]
        title = "".join(self["title"])
        content = "".join(self["content"])
        answer_num = extract_num("".join(self["answer_num"]))
        comments_num = extract_num("".join(self["comments_num"]))
        if len(self["watch_user_num"]) == 2:
            watch_user_num = int(self["watch_user_num"][0])
            click_num = int(self["watch_user_num"][1])
        else:
            watch_user_num = int(self["watch_user_num"][0])
            click_num = 0
        crawl_time = datetime.datetime.now().strftime(SQL_DATETIME_FORMAT)
        params = (zhihu_id, topics, url, title, content, answer_num, comments_num,
                  watch_user_num, click_num, crawl_time)
        return insert_sql, params


class ZhihuAnswerItem(scrapy.Item):
    #知乎的问题回答item
    zhihu_id = scrapy.Field()
    url = scrapy.Field()
    question_id = scrapy.Field()
    author_id = scrapy.Field()
    content = scrapy.Field()
    parise_num = scrapy.Field()
    comments_num = scrapy.Field()
    create_time = scrapy.Field()
    update_time = scrapy.Field()
    crawl_time = scrapy.Field()

    def get_insert_sql(self):
        #插入知乎answer表的sql语句
        insert_sql = """
            insert into zhihu_answer(zhihu_id, url, question_id, author_id, content, parise_num, comments_num,
              create_time, update_time, crawl_time
              ) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
              ON DUPLICATE KEY UPDATE content=VALUES(content), comments_num=VALUES(comments_num), parise_num=VALUES(parise_num),
              update_time=VALUES(update_time)
        """

        create_time = datetime.datetime.fromtimestamp(self["create_time"]).strftime(SQL_DATETIME_FORMAT)
        update_time = datetime.datetime.fromtimestamp(self["update_time"]).strftime(SQL_DATETIME_FORMAT)
        params = (
            self["zhihu_id"], self["url"], self["question_id"],
            self["author_id"], self["content"], self["parise_num"],
            self["comments_num"], create_time, update_time,
            self["crawl_time"].strftime(SQL_DATETIME_FORMAT),
        )

        return insert_sql, params

pipelines.py

class MysqlTwistedPipeline(object):
    def __init__(self, dbpool):
        self.dbpool = dbpool

    @classmethod
    def from_settings(cls, settings):
        dbparms = dict(
            host = settings["MYSQL_HOST"],
            db = settings["MYSQL_DBNAME"],
            user = settings["MYSQL_USER"],
            passwd = settings["MYSQL_PASSWORD"],
            charset='utf8',
            cursorclass=MySQLdb.cursors.DictCursor,
            use_unicode=True,
        )
        dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms)

        return cls(dbpool)

    def process_item(self, item, spider):
        #使用twisted将mysql插入变成异步执行
        query = self.dbpool.runInteraction(self.do_insert, item)
        query.addErrback(self.handle_error, item, spider) #处理异常

    def handle_error(self, failure, item, spider):
        # 处理异步插入的异常
        print (failure)

    def do_insert(self, cursor, item):
        #执行具体的插入
        #根据不同的item 构建不同的sql语句并插入到mysql中
        insert_sql, params = item.get_insert_sql()
        cursor.execute(insert_sql, params)

运行主程序，爬虫也在成功进行着，然而当我刷新数据库时，发现了问题。

answer的爬取很正常，然而question的爬取不仅数量少，而且字段也没完全解析出来。再仔细观察answer的数据，发现并不是将一个问题的所有回答都给爬取下来了，2000+的回答，只能爬取到200+就爬另一个问题的答案了。跟自己的代码逻辑不一样，我想着可能是自己的代理数量不够，遭到了知乎的反爬虫限制。answer表的爬取总体上来说还是成功的。

打了断点测试，发现一个问题

前面都正确，到了watch_user_num这块就死了，我去，啥鬼。打开这个url去那个网页，打开网页调试器，查看css字段，再看看自己的css逻辑，没有错，不知道怎么就停了。还有一种情况时全部提取出来了，就是在写入数据表那块失败，郁闷。得慢慢打断点调试，找原因。