python 爬取伯乐在线完整版

Posted 2020-10-28 lin1318

在jobbole.py

import scrapy
import re
import datetime
from urllib import parse
from scrapy.http import Request
from ArticleSpider.items import JobBoleArticleItem
from ArticleSpider.utils.common import get_md5
from scrapy.loader import ItemLoader
class JobboleSpider(scrapy.Spider):
    name = ‘jobbole‘
    allowed_domains = [‘blog.jobbole.com‘]
    start_urls = [‘http://blog.jobbole.com/all-posts‘]

    def parse(self, response):
        """
                1. 获取文章列表页中的文章url并交给scrapy下载后并进行解析
                2. 获取下一页的url并交给scrapy进行下载， 下载完成后交给parse
                """
        # 解析列表页中的所有文章url并交给scrapy下载后并进行解析
        post_nodes = response.css("#archive .floated-thumb .post-thumb a")
        for post_node in post_nodes:
            #获取封面图的url
            image_url = post_node.css("img::attr(src)").extract_first("")
            post_url = post_node.css("::attr(href)").extract_first("")
            #request下载完成之后，回调parse_detail进行文章详情页的解析
            # Request(url=post_url,callback=self.parse_detail)

            yield Request(url=parse.urljoin(response.url,post_url),meta={"front_image_url":image_url},callback=self.parse_detail)
            #遇到href没有域名的解决方案
            #response.url + post_url

        # 提取下一页并交给scrapy进行下载
        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):

        # front_image_url = response.meta.get("front_image_url", "")  #文章封面图
        # title = response.css(".entry-header h1::text").extract_first()
        # 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::text").extract()
        # content = response.css(‘div.entry‘).extract_first()
        #
        # 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)
        # try:
        #     create_date = datetime.datetime.strptime(create_date, "%Y/%m/%d").date()
        # except Exception as e:
        #     create_date = datetime.datetime.now().date()
        # article_item = JobBoleArticleItem()
        # article_item["title"] = title
        # article_item["url"] = response.url
        # 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
        # article_item["url_object_id"] = get_md5(response.url)

        front_image_url = response.meta.get("front_image_url", "")  # 文章封面图
        item_loader = ItemLoader(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")
        #调用这个方法来对规则进行解析生成item对象
        article_item = item_loader.load_item()
        yield article_item

2.main.py

from scrapy.cmdline import execute

import sys
import os

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

3.item.py

import scrapy
import datetime
import re
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(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()
#     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()
#     content = scrapy.Field()
#     tags = scrapy.Field()

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

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)
    )
    #因为tag本身是list，所以要重写
    tags = scrapy.Field(
        input_processor=MapCompose(remove_comment_tags),
        output_processor=Join(",")
    )
    content = scrapy.Field()

4.pipelines.py

import codecs
import json
import MySQLdb
import MySQLdb.cursors
from twisted.enterprise import adbapi
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exporters import JsonItemExporter
class ArticlespiderPipeline(object):
    def process_item(self, item, spider):
        return item
class ArticleImagePipeline(ImagesPipeline):
    #重写该方法可从result中获取到图片的实际下载地址
    def item_completed(self, results, item, info):
        for ok, value in results:
            image_file_path = value["path"]
        item["front_image_path"] = image_file_path

        return item
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,
        )
        #**dbparms-->("MySQLdb",host=settings[‘MYSQL_HOST‘]
        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, params = item.get_insert_sql()
        cursor.execute(insert_sql, params)
class JsonWithEncodingPipeline(object):
    # 自定义json文件的导出
    def __init__(self):
        # 使用codecs打开避免一些编码问题。
        self.file = codecs.open(‘article.json‘, ‘w‘, encoding="utf-8")

    def process_item(self, item, spider):
        # 将item转换为dict,然后调用dumps方法生成json对象，false避免中文出错
        lines = json.dumps(dict(item), ensure_ascii=False) + "\n"
        self.file.write(lines)
        return item

    # 当spider关闭的时候: 这是一个spider_closed的信号量。
    def spider_closed(self, spider):
        self.file.close()
class JsonExporterPipeline(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 MysqlPipeline(object):
    #采用同步的机制写入mysql
    def __init__(self):
        self.conn = MySQLdb.connect(‘localhost‘, ‘root‘, ‘123456‘, ‘article_spider‘, charset="utf8", use_unicode=True)
        self.cursor = self.conn.cursor()

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

　　5.setting.py

import os
BOT_NAME = ‘ArticleSpider‘

SPIDER_MODULES = [‘ArticleSpider.spiders‘]
NEWSPIDER_MODULE = ‘ArticleSpider.spiders‘


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘ArticleSpider (+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‘,
#}

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

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘ArticleSpider.middlewares.ArticlespiderDownloaderMiddleware‘: 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 = {
   ‘ArticleSpider.pipelines.ArticlespiderPipeline‘: 300,
    # ‘scrapy.pipelines.images.ImagesPipeline‘: 1,
    # ‘ArticleSpider.pipelines.ArticleImagePipeline‘:1,
    ‘ArticleSpider.pipelines.JsonExporterPipeline‘:2,
    # ‘ArticleSpider.pipelines.MysqlPipeline‘: 4,
}
IMAGES_URLS_FIELD = "front_image_url"
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir, ‘images‘)

# 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‘
MYSQL_HOST = "localhost"
MYSQL_DBNAME = "article_spider"
MYSQL_USER = "root"
MYSQL_PASSWORD = "123456"