Scrapy爬取伯乐在线文章

首先搭建虚拟环境,创建工程

scrapy startproject ArticleSpider
cd ArticleSpider
scrapy genspider jobbole blog.jobbole.com

修改 start_urls = ['http://blog.jobbole.com/all-posts/']

获取网页信息

ArticleSpider/spiders/jobbole.py

# -*- coding: utf-8 -*-
import datetime
import re
from urllib import parse
import scrapy
from scrapy import Request

from ArticleSpider.items import JobBoleArticleItem
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. 从文章列表中获取文章链接交给scrapy下载 再进行解析
        2. 获取下一页的链接并交给scrapy下载, 下载完成后在使用parse函数进行解析
        :param response:
        :return:
        """
        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("")
            post_url = post_node.css("::attr(href)").extract_first("")
            yield Request(url=parse.urljoin(response.url, post_url), meta={"front_image_url": image_url},
                          callback=self.parse_detail)

        # 提取下一页
        next_url = response.css(".next.page-numbers::attr(href)").extract_first()
        if next_url:
            yield Request(url=parse.urljoin(response.url, next_url), callback=self.parse)

    def parse_detail(self, response):
        """
        获取具体字段
        :param response:
        :return:
        """
        article_item = JobBoleArticleItem()

        # 通过css选择器提取字段
        front_image_url = response.meta.get("front_image_url", "")  #文章封面图
        title = response.css(".entry-header h1::text").extract()[0]
        create_date = response.css("p.entry-meta-hide-on-mobile::text").extract()[0].strip().replace("·","").strip()
        praise_nums = response.css(".vote-post-up h10::text").extract()[0]
        fav_nums = response.css(".bookmark-btn::text").extract()[0]
        match_re = re.match(".*?(\d+).*", fav_nums)
        if match_re:
            fav_nums = int(match_re.group(1))
        else:
            fav_nums = 0

        comment_nums = response.css("a[href='#article-comment'] span::text").extract()[0]
        match_re = re.match(".*?(\d+).*", comment_nums)
        if match_re:
            comment_nums = int(match_re.group(1))
        else:
            comment_nums = 0

        content = response.css("div.entry").extract()[0]

        tag_list = response.css("p.entry-meta-hide-on-mobile a::text").extract()
        tag_list = [element for element in tag_list if not element.strip().endswith("评论")]
        tags = ",".join(tag_list)

        article_item["url_object_id"] = get_md5(response.url)
        article_item["title"] = title
        article_item["url"] = response.url
        try:
            create_date = datetime.datetime.strptime(create_date, "%Y/%m/%d").date()
        except Exception as e:
            create_date = datetime.datetime.now().date()
        article_item["create_date"] = create_date
        article_item["front_image_url"] = [front_image_url]
        article_item["praise_nums"] = praise_nums
        article_item["comment_nums"] = comment_nums
        article_item["fav_nums"] = fav_nums
        article_item["tags"] = tags
        article_item["content"] = content
        yield article_item

ArticleSpider/items.py

class JobBoleArticleItem(scrapy.Item):
    title = scrapy.Field()
    create_date = scrapy.Field()
    url = scrapy.Field()
    url_object_id = scrapy.Field()
    front_image_url = scrapy.Field()
    front_image_path = scrapy.Field()
    praise_nums = scrapy.Field()
    comment_nums = scrapy.Field()
    fav_nums = scrapy.Field()
    tags = scrapy.Field()
    content = scrapy.Field()

ArticleSpider/pipelines.py

from scrapy.pipelines.images import ImagesPipeline

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

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

        return item

ArticleSpider/settings.py

创建一个文件夹ArticleSpider/images,用来保存图片

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'ArticleSpider.pipelines.ArticlespiderPipeline': 300,
    # 'scrapy.pipelines.images.ImagesPipeline': 1,
    'ArticleSpider.pipelines.ArticleImagePipeline': 1,
}

IMAGES_URLS_FIELD = "front_image_url"
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir, 'images')

数据入库

/*
Navicat MySQL Data Transfer

Source Server         : 2233
Source Server Version : 50723
Source Host           : localhost:3306
Source Database       : article_spider

Target Server Type    : MYSQL
Target Server Version : 50723
File Encoding         : 65001

Date: 2018-10-15 11:19:07
*/

SET FOREIGN_KEY_CHECKS=0;

-- ----------------------------
-- Table structure for jobbole_article
-- ----------------------------
DROP TABLE IF EXISTS `jobbole_article`;
CREATE TABLE `jobbole_article` (
  `title` varchar(255) NOT NULL,
  `create_date` date DEFAULT NULL,
  `url` varchar(255) NOT NULL,
  `url_object_id` varchar(50) NOT NULL,
  `front_image_url` varchar(255) DEFAULT NULL,
  `front_image_path` varchar(255) DEFAULT NULL,
  `praise_nums` int(11) NOT NULL DEFAULT '0',
  `comment_nums` int(11) NOT NULL DEFAULT '0',
  `fav_nums` int(11) NOT NULL DEFAULT '0',
  `tags` varchar(255) DEFAULT NULL,
  `content` longtext NOT NULL,
  PRIMARY KEY (`url_object_id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

编写pipline

import MySQLdb
import MySQLdb.cursors
from scrapy.pipelines.images import ImagesPipeline
from twisted.enterprise import adbapi

from ArticleSpider import settings
from ArticleSpider.settings import MYSQL_DBNAME, MYSQL_PASSWORD, MYSQL_USER, MYSQL_HOST

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

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

        return item

class MysqlPipeline(object):
    # 采用同步的机制写入mysql
    def __init__(self):
        self.conn = MySQLdb.connect(MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, MYSQL_DBNAME, charset="utf8",
                                    use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql = """
            insert into jobbole_article(title, url,url_object_id, create_date, fav_nums)
            VALUES (%s, %s, %s, %s, %s)
        """
        self.cursor.execute(insert_sql,
                            (item["title"], item["url"], item["url_object_id"], item["create_date"], item["fav_nums"]))
        self.conn.commit()

class MysqlTwistedPipline(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
        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
        # 根据不同的item 构建不同的sql语句并插入到mysql中
        insert_sql = """
                    insert into jobbole_article(title, url,url_object_id, create_date, front_image_url, front_image_path, praise_nums, comment_nums,fav_nums, tags,content )
                    VALUES (%s, %s, %s, %s,%s,%s, %s, %s, %s,%s,%s)
                """
        cursor.execute(insert_sql,
                       (item["title"], item["url"], item["url_object_id"], item["create_date"], item["front_image_url"],
                        item["front_image_path"], item["praise_nums"], item["comment_nums"], item["fav_nums"], item["tags"],
                        item["content"]))

settings.py

ITEM_PIPELINES = {
    # 'ArticleSpider.pipelines.ArticlespiderPipeline': 300,
    # 'scrapy.pipelines.images.ImagesPipeline': 1,
    'ArticleSpider.pipelines.ArticleImagePipeline': 1,
    'ArticleSpider.pipelines.MysqlTwistedPipline': 2
}

item loader

ArticleSpider/spiders/jobbole.py

        # 通过item loader加载item
        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("url_object_id", get_md5(response.url))
        item_loader.add_css("create_date", "p.entry-meta-hide-on-mobile::text")
        item_loader.add_value("front_image_url", [front_image_url])
        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

ArticleSpider/items.py

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

def date_convert(value):
    try:
        create_date = datetime.datetime.strptime(value, "%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 JobBoleArticleItem(scrapy.Item):
    title = scrapy.Field()
    create_date = scrapy.Field(
        input_processor=MapCompose(date_convert),
    )
    url = scrapy.Field()
    url_object_id = scrapy.Field()
    front_image_url = scrapy.Field(
        output_processor=MapCompose(return_value)
    )
    front_image_path = scrapy.Field()
    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()
    ```