Python实战---使用Scrapy+ Selenium+ChromeDriver爬取简书所有文章

使用Scrapy+ Selenium+ChromeDriver爬取简书所有文章

创建项目

scrapy startproject jianshu

创建爬虫

scrapy genspider -t crawl jianshu “jianshu.com”

运行爬虫

scrapy crawl jianshu

或者创建start.py文件

from scrapy import cmdline
cmdline.execute('scrapy crawl jianshu'.split())

然后使用PyCharm打开项目

下面开始编写代码

1、jianshu.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
import re
import requests
import json
from jianshu_spider.items import JianshuSpiderItem

class JianshuSpider(CrawlSpider):
    name = 'jianshu'
    allowed_domains = ['jianshu.com']
    start_urls = ['https://www.jianshu.com/']

    rules = (
    	# 编写匹配规则，简书文章的url只有中间12位不一样。
        Rule(LinkExtractor(allow=r'.*/p/[0-9a-z]{12}.*'), callback='parse_detail', follow=True),
    )

    def parse_detail(self, response):
        title = response.xpath('//h1[@class="_1RuRku"]/text()').get()
        author = response.xpath('//span[@class = "FxYr8x"]/a/text()').get()
        head_profile = response.xpath('//img[@class = "_13D2Eh"]/@src').get()
        pub_time = response.xpath('//time/text()').get()
        read_count = re.search(r'\d+',response.xpath('//div[@class = "s-dsoj"]/span[last()]').get()).group()
        work_count = re.search(r'\d+',response.xpath('//div[@class = "s-dsoj"]/span[last()-1]').get()).group()
        content = response.xpath('//article').get()
        subjects_id = re.search(r'\d+',response.xpath('//meta[@property="al:android:url"]/@content').get()).group()
        subjects = self.get_subject(subjects_id)
        article_id = re.search(r'.*/p/(.*)',response.xpath('//meta[@http-equiv = "mobile-agent" ]/@content').get()).group(1)
        article_url = response.url
        item = JianshuSpiderItem(
            title = title,
            author = author,
            head_profile = head_profile,
            pub_time = pub_time,
            read_count = read_count,
            work_count = work_count,
            content = content,
            subjects = subjects,
            article_id = article_id,
            article_url = article_url
        )
        yield item

	# 爬取文章所在的专题
	#使用requests重新请求，获取专题列表并返回。
    def get_subject(self,subjects_id):
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'
        }
        subjects_url = 'https://www.jianshu.com/shakespeare/notes/{}/included_collections?page=1&count=7'.format(
            subjects_id)
        resp = json.loads(requests.get(url=subjects_url,headers=headers).text)
        total_pages = resp['total_pages']
        subjects = []
        for page in range(1, total_pages + 1):
            subjects_url = 'https://www.jianshu.com/shakespeare/notes/{}/included_collections?page=1&count=7'.format(
                subjects_id)
            resp = json.loads(requests.get(url=subjects_url,headers=headers).text)
            collections = resp['collections']
            for collection in collections:
                subject = collection['title']
                subjects.append(subject)
        subjects = ','.join(subjects)
        return subjects

2、items.py

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

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

import scrapy


class JianshuSpiderItem(scrapy.Item):
    title = scrapy.Field()  # 标题
    author = scrapy.Field()  # 作者
    head_profile = scrapy.Field()  # 头像
    pub_time = scrapy.Field()  # 发布时间
    read_count = scrapy.Field()  # 阅读数
    work_count = scrapy.Field()  # 字数
    content = scrapy.Field()  # 文章内容
    subjects = scrapy.Field()  # 文章专题
    article_id = scrapy.Field()  # 文章id
    article_url = scrapy.Field()  # 文章url

3、middlewares.py

使用selenium+webdriver来请求url

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

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals
from selenium import webdriver
import time
from scrapy.http.response.html import HtmlResponse

class JianshuSeleniumDownloadMiddleware(object):
    def __init__(self):
        self.driver = webdriver.Chrome(executable_path=r'D:\Driver\chromedriver.exe')

    def process_request(self,request,spider):
        self.driver.get(request.url)
        time.sleep(2)
        # try:
        #     while True:
        #         show_more = self.driver.find_element_by_class_name('H7E3vT')
        #         show_more.click()
        #         time.sleep(2)
        #         if not show_more:
        #             break
        # except:
        #     pass
        source = self.driver.page_source
        # 将重新组装的response返回给scrapy框架解析
        response = HtmlResponse(url=self.driver.current_url,body=source,request=request,encoding='utf-8')
        return response

4、pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

import pymysql

class JianshuSpiderPipeline:
    def __init__(self):
        dbparams = {
            'host': '127.0.0.1',
            'port': 3306,
            'user': 'root',
            'password': 'root',
            'database': 'jianshu',
            'charset': 'utf8'
        }
        self.conn = pymysql.connect(**dbparams)
        self.cursor = self.conn.cursor()
        self._sql = None

    def process_item(self, item, spider):
        self.cursor.execute(self.insert_sql,(
            item['title'],
            item['author'],
            item['head_profile'],
            item['pub_time'],
            item['read_count'],
            item['work_count'],
            item['content'],
            item['subjects'],
            item['article_id'],
            item['article_url']
        ))
        print('第%s条数据即将被插入' % self.conn.insert_id())
        self.conn.commit()
        return item

    @property
    def insert_sql(self):
        if not self._sql:
            self._sql = """
            insert into article
            (id,title,author,head_profile,pub_time,read_count,work_count,content,subjects,article_id,article_url)
            values (null,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
            """
            return self._sql
        return self._sql

5、settings.py

把其中相关的设置打开

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

# Scrapy settings for jianshu_spider project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'jianshu_spider'

SPIDER_MODULES = ['jianshu_spider.spiders']
NEWSPIDER_MODULE = 'jianshu_spider.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jianshu_spider (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'jianshu_spider.middlewares.JianshuSpiderSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'jianshu_spider.middlewares.JianshuSeleniumDownloadMiddleware': 543,
}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'jianshu_spider.pipelines.JianshuSpiderPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

6、结果展示

存入到mysql数据库中

7、总结

博主没有完全爬取完毕，作为练习，爬取了一段时间就停止掉了。
如果您有需要，可以爬取所有的文章，之后再做相关分析。
项目的连接和sql文件在下面连接，需要的自行下载即可

项目源码和sql文件