2019.1.20 class124 爬取简书并且保存到数据库。看我直播的人可以来这里拉源代码

看我直播的人可以来这里拉源代码,但是如果相关的库没有安装，你是无法运行的。如果，需要库的请到我直播间咨询我会发截图给你，安装好库后，你就可以直接运行~~~请勿用于商用谢谢。

js.py

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


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

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

    def parse_detail(self, response):
        title = response.xpath("//h1[@class='title']/text()").get()
        avatar = response.xpath("//a[@class='avatar']/img/@src").get()
        author = response.xpath("//span[@class='name']/a/text()").get()
        pub_time = response.xpath("//span[@class='publish-time']/text()").get().replace("*", "")
        url = response.url
        url1 = url.split("?")[0]
        article_id =url.split('/')[-1]

        content = response.xpath("//div[@class='show-content']").get()

        word_count = response.xpath("//span[@class='wordage']/text()").get()
        comment_count = response.xpath("//span[@class='comments-count']/text()").get()
        read_count = response.xpath("//span[@class='views-count']/text()").get()
        like_count = re
        sponse.xpath("//span[@class='likes-count']/text()").get()

        subjects = ",".join(response.xpath("//div[@class='include-collection']/a/div/text()").getall())

        item = ArticleItem(
            title=title,
            avatar=avatar,
            author=author,
            pub_time=pub_time,
            origin_url=response.url,
            article_id=article_id,
            content=content,
            subjects=subjects,
            word_count=word_count,
            comment_count=comment_count,
            read_count=read_count,
            like_count=like_count
        )
        yield item

items.py

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

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

import scrapy


class ArticleItem(scrapy.Item):
    title = scrapy.Field()
    content = scrapy.Field()
    article_id = scrapy.Field()
    origin_url = scrapy.Field()
    author = scrapy.Field()
    avatar = scrapy.Field()
    pub_time = scrapy.Field()
    read_count = scrapy.Field()
    like_count = scrapy.Field()
    word_count = scrapy.Field()
    comment_count = scrapy.Field()
    subjects = scrapy.Field()


#https://www.toutiao.com/group/6633589561291178253
# https://www.toutiao.com/a6633589561291178253/

middlewares.py

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

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

from scrapy import signals


class JanshuSpiderSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class JanshuSpiderDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import pymysql
class JanshuSpiderPipeline(object):
    def __init__(self):
        dpparms={
             'host': '127.0.0.1',
            'port': 3306,
            'user': 'root',
            'password': '7923161',
            'database': 'jianshu21',
            '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.sql,)
        return item

    @property
    def sql(self):
        if not self._sql:
            self._sql="""insert into article(id,title,content,author,avatar,pub_time,origin_url,article_id) values(null,%s,%s,%s,%s,%s,%s,%s)
            """
            return self._sql
    return self._sql

settings.py

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

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

BOT_NAME = 'janshu_spider'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'janshu_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://doc.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/71.0.3578.98 Safari/537.36',
}

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

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

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

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

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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'

start

from scrapy import cmdline

cmdline.execute("scrapy crawl js".split())