item loader方式提取知乎question

首先获取问题url，如图。

发现url是在a标签下的href，所以使用css选择器即可得到。但是在这里，看到后面的url并不是完整的url，缺少主域名，这时就要用到urllib中的parse，将主域名与上述url连接起来。做个测试，发现可以。如下图

但是为了防止爬到javascript,还是需要对url做过滤，使用filter.代码如下

在这么多url中，我只对问题url感兴趣，所以要做正则表达式的匹配提取。

还有这种url中也要提取出question url

首先在item中创建好问题item和答案item

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()
    crawl_update_time = scrapy.Field()


class ZhihuAnswerItem(scrapy.Field):
    #知乎的答案item
    zhihu_id = scrapy.Field()
    url = scrapy.Field()
    question_id = scrapy.Field()
    author_id = scrapy.Field()
    content = scrapy.Field()
    praise_num = scrapy.Field()
    comments_num = scrapy.Field()
    watcher_user_num = scrapy.Field()
    click_num = scrapy.Field()
    crawl_time = scrapy.Field()
    crawl_update_time = scrapy.Field()

下面看看如何通过css选择器获取具体的字段，这里只以title的获取为例，其他都是类似的

# -*- 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", ".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_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
        pass

    def parse_answer(self, reponse):
        pass

    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)]

打断点进行调试