Python爬蟲框架Scrapy實例(一)


目標任務:爬取騰訊社招信息,需要爬取的內容為:職位名稱,職位的詳情鏈接,職位類別,招聘人數,工作地點,發布時間。

一、創建Scrapy項目

scrapy startproject Tencent

命令執行后,會創建一個Tencent文件夾,結構如下

二、編寫item文件,根據需要爬取的內容定義爬取字段

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

import scrapy

class TencentItem(scrapy.Item):

    # 職位名
    positionname = scrapy.Field()
    # 詳情連接
    positionlink = scrapy.Field()
    # 職位類別
    positionType = scrapy.Field()
    # 招聘人數
    peopleNum = scrapy.Field()
    # 工作地點
    workLocation = scrapy.Field()
    # 發布時間
    publishTime = scrapy.Field()

三、編寫spider文件

進入Tencent目錄,使用命令創建一個基礎爬蟲類:

#  tencentPostion為爬蟲名,tencent.com為爬蟲作用范圍
scrapy genspider tencentPostion "tencent.com"

執行命令后會在spiders文件夾中創建一個tencentPostion.py的文件,現在開始對其編寫:

# -*- coding: utf-8 -*-
import scrapy
from tencent.items import TencentItem

class TencentpositionSpider(scrapy.Spider):
    """
    功能:爬取騰訊社招信息
    """
    # 爬蟲名
name
= "tencentPosition"
# 爬蟲作用范圍
allowed_domains = ["tencent.com"] url = "http://hr.tencent.com/position.php?&start=" offset = 0 # 起始url start_urls = [url + str(offset)] def parse(self, response): for each in response.xpath("//tr[@class='even'] | //tr[@class='odd']"): # 初始化模型對象 item = TencentItem() # 職位名稱 item['positionname'] = each.xpath("./td[1]/a/text()").extract()[0] # 詳情連接 item['positionlink'] = each.xpath("./td[1]/a/@href").extract()[0] # 職位類別 item['positionType'] = each.xpath("./td[2]/text()").extract()[0] # 招聘人數 item['peopleNum'] = each.xpath("./td[3]/text()").extract()[0] # 工作地點 item['workLocation'] = each.xpath("./td[4]/text()").extract()[0] # 發布時間 item['publishTime'] = each.xpath("./td[5]/text()").extract()[0] yield item if self.offset < 1680: self.offset += 10 # 每次處理完一頁的數據之后,重新發送下一頁頁面請求 # self.offset自增10,同時拼接為新的url,並調用回調函數self.parse處理Response yield scrapy.Request(self.url + str(self.offset), callback = self.parse)

四、編寫pipelines文件

# -*- coding: utf-8 -*-
import json

class TencentPipeline(object):
  """
功能:保存item數據
"""
def __init__(self): self.filename = open("tencent.json", "w") def process_item(self, item, spider): text = json.dumps(dict(item), ensure_ascii = False) + ",\n" self.filename.write(text.encode("utf-8")) return item def close_spider(self, spider): self.filename.close()

五、settings文件設置(主要設置內容)

# 設置請求頭部,添加url
DEFAULT_REQUEST_HEADERS = {
    "User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;",
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
}

# 設置item——pipelines
ITEM_PIPELINES = {
    'tencent.pipelines.TencentPipeline': 300,
}

執行命令,運行程序

# tencentPosition為爬蟲名
scrapy crwal tencentPosition

 

 

使用CrawlSpider類改寫

# 創建項目
scrapy startproject TencentSpider

# 進入項目目錄下,創建爬蟲文件
scrapy genspider -t crawl tencent tencent.com

item等文件寫法不變,主要是爬蟲文件的編寫

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

import scrapy
# 導入CrawlSpider類和Rule
from scrapy.spiders import CrawlSpider, Rule
# 導入鏈接規則匹配類,用來提取符合規則的連接
from scrapy.linkextractors import LinkExtractor
from TencentSpider.items import TencentItem

class TencentSpider(CrawlSpider):
    name = "tencent"
    allow_domains = ["hr.tencent.com"]
    start_urls = ["http://hr.tencent.com/position.php?&start=0#a"]

    # Response里鏈接的提取規則,返回的符合匹配規則的鏈接匹配對象的列表
    pagelink = LinkExtractor(allow=("start=\d+"))

    rules = [
        # 獲取這個列表里的鏈接,依次發送請求,並且繼續跟進,調用指定回調函數處理
        Rule(pagelink, callback = "parseTencent", follow = True)
    ]

    # 指定的回調函數
    def parseTencent(self, response):
        for each in response.xpath("//tr[@class='even'] | //tr[@class='odd']"):
            item = TencentItem()
            # 職位名稱
            item['positionname'] = each.xpath("./td[1]/a/text()").extract()[0]
            # 詳情連接
            item['positionlink'] = each.xpath("./td[1]/a/@href").extract()[0]
            # 職位類別
            item['positionType'] = each.xpath("./td[2]/text()").extract()[0]
            # 招聘人數
            item['peopleNum'] =  each.xpath("./td[3]/text()").extract()[0]
            # 工作地點
            item['workLocation'] = each.xpath("./td[4]/text()").extract()[0]
            # 發布時間
            item['publishTime'] = each.xpath("./td[5]/text()").extract()[0]

            yield item

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM