Scrapy抓取jobbole数据

1、python版本3.6.1

2、python编辑器：JetBrains PyCharm

2、安装virtualenvwrapper-win

pip3 install virtualenvwrapper-win

3、创建项目

mkvirtualenv spider_article
pip install C:UsersCRDownloadsTwisted-17.5.0-cp36-cp36m-win_amd64.whl 
pip install pypiwin32
pip install -i https://pypi.douban.com/simple/ scrapy
pip install mysqlclient
pip install pillow

4、现在项目存放位置：

　　1、打开cmd

　　2、workon  spider_article

　　3、scrapy startproject ArticleSpider

　　4、cd ArticleSpider

　　5、scrapy genspider jobbole blog.jobbole.com

5、ArticleSpider文件夹下面创建调试文件

from scrapy.cmdline import execute

import sys
import os

sys.path.append(os.path.dirname(os.path.abspath(__file__)))
execute(["scrapy","crawl","jobbole"])

6、主要代码

jobbole.py文件内容

import scrapy
import re
import datetime
from scrapy.http import Request
from urllib import parse   #python2中import urlparse
from scrapy.loader import ItemLoader


from ArticleSpider.items import JobBoleArticleItem,ArticleItemLoader

from ArticleSpider.utils.common import get_md5


class JobboleSpider(scrapy.Spider):
    name = 'jobbole'
    allowed_domains = ['blog.jobbole.com']
    start_urls = ['http://blog.jobbole.com/all-posts/']

    def parse(self, response):

        '''
        1、获取文章列表页面中的文章url并交给scrapy下载后解析
        2、获取下一页的url并交给scrapy进行下载，下载完成后交给parse
        :param response:
        :return:
        '''
        #extract 一旦执行就会返回一个数组
        post_nodes = response.css("#archive .floated-thumb .post-thumb a")
        for post_node in post_nodes:
            image_url = post_node.css("img::attr(src)").extract_first("")
            #取出当前文章的域名
            #Request(url=post_url,callback=self.parse_detail)
            post_url = post_node.css("::attr(href)").extract_first("")
            #parse.urljoin      post_url如果没有域名就从response中提取域名防进行；如果post_url有域名，response就不会起作用
            yield Request(url=parse.urljoin(response.url,post_url),meta={"front_image_url":image_url}, callback=self.parse_detail)

        #提取下一页并交给scrapy进行下载
        next_urls = response.css(".next.page-numbers::attr(href)").extract_first("")
        if next_urls:
            yield Request(url=parse.urljoin(response.url, post_url), callback=self.parse)

    def parse_detail(self,response):
        '''
        获取文章的具体字段
        :param response: 
        :return: 
        '''
        front_image_url = response.meta.get("front_image_url", "")  #文章封面图
        item_loader = ArticleItemLoader(item=JobBoleArticleItem(),response=response)
        item_loader.add_css("title",".entry-header h1::text")
        item_loader.add_value("url", response.url)
        item_loader.add_value("front_image_url",[front_image_url])
        item_loader.add_value("url_object_id",get_md5(response.url))
        item_loader.add_css("create_date", "p.entry-meta-hide-on-mobile::text")
        item_loader.add_css("praise_nums", ".vote-post-up h10::text")
        item_loader.add_css("comment_nums", "a[href='#article-comment'] span::text")
        item_loader.add_css("fav_nums", ".bookmark-btn::text")
        item_loader.add_css("tags", "p.entry-meta-hide-on-mobile a::text")
        item_loader.add_css("content", "div.entry")
        article_item = item_loader.load_item()
        yield article_item

2、items.py文件

import datetime
import re

import scrapy
from scrapy.loader import ItemLoader
from scrapy.loader.processors import MapCompose,TakeFirst,Join


class ArticlespiderItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    pass

def date_convert(vlaue):
    try:
        create_date = datetime.datetime.strptime(vlaue,"%Y/%m/%d").date()
    except Exception as e:
        create_date = datetime.datetime.now().date()
    return create_date


def get_nums(value):
    match_re = re.match(".*?(d+).*", value)
    if match_re:
        nums = int(match_re.group(1))
    else:
        nums = 0
    return  nums

def remove_comment_tags(value):
    #去掉tag中提取的评论
    if "评论" in value:
        return ""
    else:
        return value

def return_value(value):
    return value

class ArticleItemLoader(ItemLoader):
    #自定义ItemLoader
    default_output_processor = TakeFirst()


class JobBoleArticleItem(scrapy.Item):
    title = scrapy.Field()
    # title = scrapy.Field(
    #     input_processor = MapCompose(lambda x:x+'-jobbole')
    # )
    create_date = scrapy.Field(
        input_processor = MapCompose(date_convert),
        #output_processor = TakeFirst(),#只取第一个
    )
    url = scrapy.Field()
    url_object_id = scrapy.Field()
    front_image_url = scrapy.Field()
    front_image_path = scrapy.Field(
        input_processor=MapCompose(return_value)
    )
    praise_nums = scrapy.Field(
        input_processor = MapCompose(get_nums)
    )
    comment_nums = scrapy.Field(
        input_processor = MapCompose(get_nums)
    )
    fav_nums = scrapy.Field(
        input_processor = MapCompose(get_nums)
    )
    tags = scrapy.Field(
        input_processor=MapCompose(remove_comment_tags),
        output_processor=Join(",")
    )
    content = scrapy.Field()

3、piplines.py文件

import codecs
import json

from scrapy.pipelines.images import ImagesPipeline
from scrapy.exporters import JsonItemExporter
from twisted.enterprise import adbapi  #adbapi可以将MySQLdb的一些操作变成异步化的操作

import MySQLdb
import MySQLdb.cursors

class ArticlespiderPipeline(object):
    def process_item(self, item, spider):
        return item

class JsonWithEncodingPipeline(object):
    #自定义json文件的导出
    def __init__(self):
        self.file = codecs.open('article.json','w',encoding="utf-8")

    def process_item(self, item, spider):
        lines = json.dumps(dict(item),ensure_ascii=False) + '
'
        self.file.write(lines)
        return item

    def spider_closed(self,spider):
        self.file.close()

class MysqlPipeline(object):
    def __init__(self):
        self.conn = MySQLdb.connect("localhost","root","","article_spider",charset="utf8",use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        inset_sql = '''
            INSERT INTO  article (title,url,create_date,fav_nums)
            VALUES (%s,%s,%s,%s)
        '''
        self.cursor.execute(inset_sql,(item['title'],item['url'],item['create_date'],item['fav_nums']))
        self.conn.commit()

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
       :param item:
       :param spider:
       :return:
       '''
       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
        inset_sql = '''
            INSERT INTO  article (title,url,create_date,fav_nums)
            VALUES (%s,%s,%s,%s)
        '''
        cursor.execute(inset_sql, (item['title'], item['url'], item['create_date'], item['fav_nums']))


class JsonExporterPipleline(object):
    #调用scrapy提供的json export导出json文件
    def __init__(self):
        self.file = open('articleexport.json', 'wb')
        self.exporter = JsonItemExporter(self.file, encoding="utf-8", ensure_ascii=False)
        self.exporter.start_exporting()

    def close_spider(self, spider):
        self.exporter.finish_exporting()
        self.file.close()


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


class ArticleImagePipline(ImagesPipeline):
    def item_completed(self, results, item, info):
        if "front_image_path" in item:
            for ok,value in results:
                image_file_path = value["path"]
            item["front_image_path"] = image_file_path

        return item

4、创建公共函数（位置存放ArticleSpider/utils/common.py）

import hashlib

def get_md5(url):
    if isinstance(url,str):
        url = url.encode("utf-8")
    m = hashlib.md5()
    m.update(url)
    return m.hexdigest()

if __name__ == '__main__':
    print(get_md5("http://jobbole.com"))

5、配置settings文件

import os

ITEM_PIPELINES = {
    'scrapy.pipelines.images.ImagesPipeline':1,#图片下载
    'ArticleSpider.pipelines.MysqlTwistedPipeline': 3,
}
IMAGES_URLS_FIELD = 'front_image_url'
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir,"images")  #指定图片存储路径


MYSQL_HOST = 'localhost'
MYSQL_DBNAME = 'article_spider'
MYSQL_USER = 'root'
MYSQL_PASSWORD = ''