scrapy爬取伯乐在线文章
创建爬虫工程
(p3scrapy) [vagrant@reboot vagrant]$ scrapy startproject ArticleSpider
You can start your first spider with:
cd ArticleSpider
scrapy genspider example example.com
(p3scrapy) [vagrant@reboot ArticleSpider]$ scrapy genspider jobbole blog.jobbole.com
完整项目结构
(p3scrapy) [vagrant@reboot ArticleSpider]$ tree .
.
├── ArticleSpider
│ ├── images
│ │ └── full
│ ├── __init__.py
│ ├── items.py
│ ├── middlewares.py
│ ├── pipelines.py
│ ├── settings.py
│ ├── spiders
│ │ ├── __init__.py
│ │ ├── jobbole.py
├── main.py
└── scrapy.cfg
表结构
CREATE TABLE `article` (
`title` varchar(200) NOT NULL,
`create_date` date DEFAULT NULL,
`url` varchar(300) NOT NULL,
`url_object_id` varchar(50) NOT NULL,
`front_image_url` varchar(300) DEFAULT NULL,
`front_image_path` varchar(200) DEFAULT NULL,
`praise_nums` int(11) DEFAULT NULL,
`fav_nums` int(11) DEFAULT NULL,
`comment_nums` int(11) DEFAULT NULL,
`tags` varchar(200) DEFAULT NULL,
`content` longtext NOT NULL,
PRIMARY KEY (`url_object_id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;
jobbole.py
# -*- coding: utf-8 -*-
import scrapy, re
from scrapy.http import Request
from urllib import parse
from ArticleSpider.items import JobBoleArticleItem
from ArticleSpider.utils.common import get_md5
from datetime import datetime
from scrapy.loader import ItemLoader
from ArticleSpider.items import JobBoleArticleItem, ArticleItemLoader
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
: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)
# 提取下一页并进行下载
next_urls= response.css(".next.page-numbers::attr(href)").extract_first("")
if next_urls:
yield Request(url=parse.urljoin(response.url, next_urls), callback=self.parse)
def parse_detail(self, response):
# article_item = JobBoleArticleItem()
# # 提取文章的具体字段
# # re_selector = response.xpath("/html/body/div[3]/div[3]/div[1]/div[1]/h1")
# # re2_selector = response.xpath('//*[@id="post-110287"]/div[1]/h1')
# front_image_url = response.meta.get("front_image_url", "") # 文章封面图
# title = response.xpath('//*[@class="entry-header"]/h1/text()').extract_first("")
# create_date = response.xpath('//p[@class="entry-meta-hide-on-mobile"]/text()').extract_first("").strip().replace('·','').strip()
# praise_nums = int(response.xpath('//span[contains(@class,"vote-post-up")]/h10/text()').extract_first(""))
# fav_nums = response.xpath('//span[contains(@class,"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_first("")
# comment_re = re.match(".*?(\d+).*", comment_nums)
# comment_nums = int(comment_re.group(1)) if comment_re else 0
# # if comment_re:
# # comm_nums = int(comment_re.group(1))
# # else:
# # comm_nums = 0
# content = response.xpath('//div[@class="entry"]').extract()[0]
#
# tag_list = response.xpath('//p[@class="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.strptime(create_date, "%Y/%m/%d").date()
# except Exception as e:
# print(e.args)
# create_date = 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
# 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
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
from scrapy.loader import ItemLoader
from scrapy.loader.processors import MapCompose, TakeFirst, Join
import datetime
import re
import scrapy
class ArticlespiderItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
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()
# url = scrapy.Field()
# front_image_url = scrapy.Field()
# front_image_path = scrapy.Field()
# praise_nums = scrapy.Field()
# fav_nums = scrapy.Field()
# comment_nums = scrapy.Field()
# tags = scrapy.Field()
# content = scrapy.Field()
# url_object_id = scrapy.Field()
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()
def get_insert_sql(self):
# insert_sql = """
# insert into article(title, url, create_date, fav_nums)
# VALUES (%s, %s, %s, %s) ON DUPLICATE KEY UPDATE content=VALUES(fav_nums)
# """
# params = (self["title"], self["url"], self["create_date"], self["fav_nums"])
insert_sql = """
insert into article(title, url, create_date, fav_nums, url_object_id, praise_nums,comment_nums,tags, content, front_image_url, front_image_path)
VALUES (%s, %s, %s, %s,%s, %s, %s, %s,%s, %s, %s)
"""
params = (self['title'], self['url'],self['create_date'],self['fav_nums'], self['url_object_id'], self['praise_nums'], self['comment_nums'], self['tags'], self['content'], self['front_image_url'], self['front_image_path'])
return insert_sql, params
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
from scrapy.pipelines.images import ImagesPipeline
import codecs, json
from scrapy.exporters import JsonItemExporter
import MySQLdb
import MySQLdb.cursors
from twisted.enterprise import adbapi
class ArticlespiderPipeline(object):
def process_item(self, item, spider):
return item
class JsonWithEncodingPipeline(object):
# 自定义json文件的导出
"""写入json文件"""
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) + '\n'
self.file.write(lines)
return item
def spider_closed(self,spider):
self.file.close()
class MysqlPipeline(object):
# 采用同步的方式写入mysql数据库
def __init__(self):
self.conn = MySQLdb.connect('127.0.0.1', 'root', '123456', 'articlespider', charset="utf8", use_unicode=True)
self.cursor = self.conn.cursor()
def process_item(self, item, spider):
insert_sql = """
insert into article(title, url, create_date, fav_nums, url_object_id, front_image_path, praise_nums,comment_nums,tags,content,front_image_url)
VALUES (%s, %s, %s, %s,%s, %s, %s, %s,%s, %s, %s)
"""
self.cursor.execute(insert_sql, (item['title'], item['url'],item['create_date'],item['fav_nums'], item['url_object_id'], item['front_image_path'],item['praise_nums'],item['comment_nums'],item['tags'],item['content'],item['front_image_url']))
self.conn.commit()
class MysqlTwistedPipeline(object):
# 采用异步的方式写入mysql数据库
def __init__(self, dbpool):
self.dbpool = dbpool
@classmethod
def from_settings(cls, settings):
dbparms = dict(
host=settings["MYSQL_HOST"],
user=settings["MYSQL_USER"],
password=settings["MYSQL_PASSWORD"],
db=settings["MYSQL_DBNAME"],
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)
# 处理异常
query.addErrback(self.handle_error)
def handle_error(self, failure):
# 处理异步插入的异常
print(failure)
def do_insert(self, cursor, item):
# 执行具体的插入逻辑
# insert_sql = """
# insert into article(title, url, create_date, fav_nums, url_object_id, front_image_path, praise_nums,comment_nums,tags, content, front_image_url)
# VALUES (%s, %s, %s, %s,%s, %s, %s, %s,%s, %s, %s)
# """
# cursor.execute(insert_sql, (item['title'], item['url'],item['create_date'],item['fav_nums'], item['url_object_id'], item['front_image_path'], item['praise_nums'], item['comment_nums'], item['tags'], item['content'], item['front_image_url']))
insert_sql, params = item.get_insert_sql()
cursor.execute(insert_sql, params)
class JsonItemExporterPipeline(object):
# 调用scrapy提供的json export导出json文件
def __init__(self):
self.file = codecs.open('articleport.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 ArticleImagePipeline(ImagesPipeline):
# 自定义图片下载
# 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
def item_completed(self, results, item, info):
print(item)
if "front_image_url" in item:
for ok, value in results:
image_file_path = value["path"]
print(image_file_path)
item["front_image_path"] = image_file_path
return item
settings.py
添加如下
MYSQL_HOST = "127.0.0.1"
MYSQL_DBNAME = "articlespider"
MYSQL_USER = "root"
MYSQL_PASSWORD = "123456"
ROBOTSTXT_OBEY = False
import sys, os
BASE_DIR = os.path.dirname(os.path.abspath(os.path.dirname(__file__)))
sys.path.insert(0, os.path.join(BASE_DIR, "ArticleSpider"))
ITEM_PIPELINES = {
# 'ArticleSpider.pipelines.ArticlespiderPipeline': 300,
# "scrapy.pipelines.images.ImagesPipeline": 1, # scrapy自带的图片下载组件
# 'ArticleSpider.pipelines.JsonWithEncodingPipeline': 2, # 自定义保存到json文件
# 'ArticleSpider.pipelines.JsonItemExporterPipeline': 2, # 使用scrapy自带的保存到json文件组件
# 'ArticleSpider.pipelines.MysqlPipeline': 2, # 同步保存模式
'ArticleSpider.pipelines.MysqlTwistedPipeline': 2, # 异步保存模式
'ArticleSpider.pipelines.ArticleImagePipeline': 1, # 自定义图片下载组件
}
# 图片下载
IMAGES_URLS_FIELD = "front_image_url"
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir, 'images')
DOWNLOAD_FAIL_ON_DATALOSS = False
main.py
启动程序
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from scrapy.cmdline import execute
import sys, os
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
# print(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# execute(["scrapy", "crawl", "jobbole"])
execute(["scrapy", "crawl", "lagou"])
采集数据结果
不要让懒惰占据你的大脑,不让要妥协拖跨你的人生。青春就是一张票,能不能赶上时代的快车,你的步伐掌握在你的脚下,good luck