欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

Scrapy加Selenium爬取简书

程序员文章站 2022-05-09 21:17:09
...

爬虫主体:

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from js_spi.items import ArticleItem


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

    rules = (
        Rule(LinkExtractor(allow=r'.*/p/[0-9a-z]{12}.*'), callback='parse_page', follow=True),
    )

    def parse_page(self, response):
        title = response.xpath('//section[@class="ouvJEz"]/h1/text()').get()
        author = response.xpath('//span[@class="FxYr8x"]/a/text()').get()
        edit_time = response.xpath('//div[@class="s-dsoj"]//time/text()').get()
        content = response.xpath('//article[@class="_2rhmJa"]').getall()
        fav_count = response.xpath('//span[@class="_1LOh_5"]/text()').get()
        text_type = '|'.join(response.xpath('//a[@class="_3s5t0Q _1OhGeD"]/span/text()').getall())
        item = ArticleItem(title=title,
                           author=author,
                           edit_time=edit_time,
                           content=content,
                           fav_count=fav_count,
                           text_type=text_type)
        yield item




item:

# -*- 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 ArticleItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    author = scrapy.Field()
    edit_time = scrapy.Field()
    content = scrapy.Field()
    fav_count = scrapy.Field()
    text_type = scrapy.Field()

    # article_id = scrapy.Field()
    # origin_url = scrapy.Field()


middleware:

# -*- 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 SeleniumDownloadMiddleware(object):
    def __init__(self):
        self.driver = webdriver.Chrome(executable_path=r'C:\ChromeDriver\chromedriver.exe')

    def process_request(self, request, spider):
        self.driver.get(request.url)
        time.sleep(1)
        try:
            while True:
                show_more = self.driver.find_element_by_class_name('H7E3vT')
                show_more.click()
                time.sleep(0.3)
                if not show_more:
                    break
        except:
            pass
        return HtmlResponse(url=request.url,
                            body=self.driver.page_source,
                            request=request,
                            encoding='utf-8',
                            status=200)

pipeline:

# -*- 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
from scrapy.exporters import JsonLinesItemExporter


class JsSpiPipeline(object):
    def open_spider(self,spider):
        self.js=open('./js.json','wb')
        self.exporter = JsonLinesItemExporter(self.js,ensure_ascii=False,encoding='utf-8')

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

    def close_spider(self,spider):
        self.js.close()

settings:

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

# Scrapy settings for js_spi 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 = 'js_spi'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'js_spi (+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/80.0.3987.132 Safari/537.36'
}

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

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'js_spi.middlewares.SeleniumDownloadMiddleware': 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 = {
   'js_spi.pipelines.JsSpiPipeline': 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'