进程池爬取并存入mongodb
设置进程池爬取拉钩网:
# coding = utf-
import json
import pymongo
import pandas as pd
import requests
from lxml import etree
import time
from multiprocessing import Pool # 设置mongodb
client = pymongo.MongoClient('localhost')
db = client['lagou']
# 查询的岗位名称
POSITION_NAME = '数据挖掘'
# 想要爬取的总页面数
PAGE_SUM =
# 每页返回的职位数量
PAGE_SIZE =
# 指定数据库的名字
DATA_NAME = "DataMiningPosition" base_url = 'https://m.lagou.com/search.json?city=%E5%85%A8%E5%9B%BD&positionName={positionName}' \
'&pageNo={pageNo}&pageSize={pageSize}' def page_index(pageno):
headers = {
"Accept": "application/json",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9",
# cookie能不要尽量不要,这里正好不用cookie也可以正常返回数据
# "Cookie": "user_trace_token=20181119151914-03711263-38a2-4d81-bd81-5f480d930039; _ga=GA1.2.605262108.1542611954; _gid=GA1.2.249787972.1542611954; LGSID=20181119151916-6c3da9fa-ebcb-11e8-8958-5254005c3644; PRE_UTM=; PRE_HOST=www.baidu.com; PRE_SITE=https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3DOnHWjpEfiW4_pVm7hX8NYOFm0iJ7bz1ZJJlaKPPnmMzLE-6ypKNo0f19ABO5bjW4%26wd%3D%26eqid%3D8f61629100016e18000000065bf263e7; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Fgongsi%2F147.html; LGUID=20181119151916-6c3dabf3-ebcb-11e8-8958-5254005c3644; index_location_city=%E5%85%A8%E5%9B%BD; JSESSIONID=ABAAABAAAGCABCC2D851CA25D1CFCD2B28DCDD6E00A2C7E; _ga=GA1.3.605262108.1542611954; X_HTTP_TOKEN=a0cc1a4beb8a41f57f144bc0bfd77bd7; sajssdk_2015_cross_new_user=1; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%221672adb3834203-08b3706084b44a-3961430f-1327104-1672adb3835428%22%2C%22%24device_id%22%3A%221672adb3834203-08b3706084b44a-3961430f-1327104-1672adb3835428%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%7D; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1542611954,1542612053,1542612277,1542612493; _gat=1; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1542613115; LGRID=20181119153837-20bafb1a-ebce-11e8-8958-5254005c3644",
"Host": "m.lagou.com",
"Proxy-Connection": "keep-alive",
"Referer": "http://m.lagou.com/search.html",
"X-Requested-With": "XMLHttpRequest",
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3',
}
url = base_url.format(positionName=POSITION_NAME, pageNo=pageno, pageSize=PAGE_SIZE)
response = requests.get(url, headers=headers)
html = response.text
content = json.loads(html)
print(content)
if content.get("content"):
return content
else:
time.sleep()
return page_index(pageno) def parse_page_index(content): for i in range():
try:
item = content['content']['data']['page']['result'][i]
#print(item)
yield {
'positionId': item.get('positionId'),
'positionName': item.get('positionName'),
'city': item.get('city'),
'createTime': item.get('createTime'),
'salary': item.get('salary'),
'companyId': item.get('companyId'),
'companyFullName': item.get('companyFullName')
}
except IndexError as e:
print('可能没有那么多字段', e) def save_to_mongo(data):
if db[DATA_NAME].update({'positionId': data['positionId']}, {'$set': data}, True):
print('Saved to Mongo', data['positionId'])
else:
print('Saved to Mongo Failed', data['positionId']) def parse_detail(url):
# url = "http://m.lagou.com/jobs/4593934.html"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36",
"Accept": "text / html, application / xhtml + xml, application / xml;q = 0.9, image / webp, image / apng, * / *;q = 0.8",
"Accept - Encoding": "gzip, deflate",
"Accept - Language": "zh - CN, zh;q = 0.9",
"Cache - Control": "max - age = 0",
"Connection": "eep - alive",
# "Cookie": "_ga=GA1.2.474762156.1528795210; _gid=GA1.2.574638607.1528795210; user_trace_token=20180612172010-cdf76dc1-6e21-11e8-9af0-525400f775ce; LGUID=20180612172010-cdf772c0-6e21-11e8-9af0-525400f775ce; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1528795210,1528795215,1528795223; index_location_city=%E5%85%A8%E5%9B%BD; X_HTTP_TOKEN=f3ed266ddeee802fb7d402e4f6d4f4a3; JSESSIONID=ABAAABAAAFDABFG9F9C52FA9D8CAE24F139A0131C45E918; _ga=GA1.3.474762156.1528795210; _gat=1; LGSID=20180612184248-597a7795-6e2d-11e8-9479-5254005c3644; PRE_UTM=; PRE_HOST=; PRE_SITE=http%3A%2F%2Fm.lagou.com%2Fsearch.html; PRE_LAND=http%3A%2F%2Fm.lagou.com%2Fjobs%2F4079910.html; LGRID=20180612184505-ab051d02-6e2d-11e8-9479-5254005c3644; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1528800306" }
try:
response = requests.get(url, headers=headers)
if response.status_code == :
print("请求成功")
text = response.content.decode()
# print(text)
html = etree.HTML(text)
workyear = html.xpath('//span[@class="item workyear"]/span/text()')
if workyear:
workyear = workyear[]
else:
time.sleep()
parse_detail(url)
positiondesc = html.xpath('//div[@class="positiondesc"]//p/text()')
#print(workyear, positiondesc)
return workyear, positiondesc
except Exception as e:
print(e) # 将爬取的数据存到Mongodb
def to_mongo(page_sum):
# 拉勾网顶多只能显示到334页
for page in range(page_sum):
html = page_index(page)
items = parse_page_index(html)
# print(items)
for item in items:
print(item)
save_to_mongo(item) # 运用进程池将爬取的数据存到Mongodb
def to_mongo_pool(page):
# 拉勾网顶多只能显示到334页
content = page_index(page)
items = parse_page_index(content)
# print(items)
for item in items:
print(item)
save_to_mongo(item) # 解析爬取的字条,以便把数据转为DataFrame格式
def parse_items(page_sum):
for page in range(page_sum):
html = page_index(page)
items = parse_page_index(html)
for item in items:
positionId = item["positionId"]
detail_url = "http://m.lagou.com/jobs/{}.html".format(positionId)
workyear, positiondesc = parse_detail(detail_url)
print(positionId,positiondesc)
yield [
item["positionId"],
item["positionName"],
item["city"],
item["createTime"],
item["salary"],
item["companyId"],
item["companyFullName"],
workyear,
positiondesc
] # 把数据保存为csv格式
def to_csv(page_sum):
item_lists = []
# print(parse_items())
for item in parse_items(page_sum):
item_lists.append(item)
#print(item_lists)
data = pd.DataFrame(item_lists,
columns=["positionId", "positionName", "city", "createTime", "salary", "companyId",
"companyFullName", "workyear", "positiondesc"])
data.to_csv("python_positon.csv") if __name__ == '__main__': #to_csv
#to_mongo()
# 建议保存到mongodb数据库中 start_time = time.time()
pool = Pool() # pool()参数:进程个数:默认的是电脑cpu的核的个数,如果要指定进程个数,这个进程个数要小于等于cpu的核数
# 第一个参数是一个函数体,不需要加括号,也不需指定参数。。
# 第二个参数是一个列表,列表中的每个参数都会传给那个函数体
pool.map(to_mongo_pool,[i for i in range(PAGE_SUM)])
# close它只是把进程池关闭
pool.close()
# join起到一个阻塞的作用,主进程要等待子进程运行完,才能接着往下运行
pool.join()
end_time = time.time()
print("总耗费时间%.2f秒" % (end_time - start_time))
进程池爬取并存入mongodb的更多相关文章
- python进程池爬取下载美女图片(xpath)--lowbiprogrammer
# -*- coding: utf-8 -*-import requests,osfrom lxml import etreeimport multiprocessingfrom retrying i ...
- 基于requests模块的cookie,session和线程池爬取
目录 基于requests模块的cookie,session和线程池爬取 基于requests模块的cookie操作 基于requests模块的代理操作 基于multiprocessing.dummy ...
- 5 使用ip代理池爬取糗事百科
从09年读本科开始学计算机以来,一直在迷茫中度过,很想学些东西,做些事情,却往往陷进一些技术细节而蹉跎时光.直到最近几个月,才明白程序员的意义并不是要搞清楚所有代码细节,而是要有更宏高的方向,要有更专 ...
- Python使用Scrapy框架爬取数据存入CSV文件(Python爬虫实战4)
1. Scrapy框架 Scrapy是python下实现爬虫功能的框架,能够将数据解析.数据处理.数据存储合为一体功能的爬虫框架. 2. Scrapy安装 1. 安装依赖包 yum install g ...
- Python爬虫-代理池-爬取代理入库并测试代理可用性
目的:建立自己的代理池.可以添加新的代理网站爬虫,可以测试代理对某一网址的适用性,可以提供获取代理的 API. 整个流程:爬取代理 ----> 将代理存入数据库并设置分数 ----> 从数 ...
- 42.scrapy爬取数据入库mongodb
scrapy爬虫采集数据存入mongodb采集效果如图: 1.首先开启服务切换到mongodb的bin目录下 命令:mongod --dbpath e:\data\db 另开黑窗口 命令:mongo. ...
- 使用requests、BeautifulSoup、线程池爬取艺龙酒店信息并保存到Excel中
import requests import time, random, csv from fake_useragent import UserAgent from bs4 import Beauti ...
- 使用requests、re、BeautifulSoup、线程池爬取携程酒店信息并保存到Excel中
import requests import json import re import csv import threadpool import time, random from bs4 impo ...
- 19 03 13 关于 scrapy 框架的 对环球网的整体爬取(存储于 mongodb 数据库里)
关于 spinder 在这个框架里面 和不用数据库 相同 # -*- coding: utf-8 -*- import scrapy from yang_guan.items import ...
随机推荐
- SRM 600 div 2 T 2
题意:给你50个数,问你最少去掉多少数能使得剩下的数不可能具备子集S,OR起来为goal 如果一个数不是goal的子状态,那么我们没必要删除他,所以我们只关心goal的子状态的数 1:如果所有的数OR ...
- numpy的使用方法
一.numpy快速入门 1.什么是numpy: numpy是python的一个矩阵类型,提供了大量矩阵处理的函数,非正式来说,就是一个使运算更容易,执行更迅速的库,因为它的内部运算是通过c语言而不是p ...
- R语言:提取路径中的文件名字符串(basename函数)
假设存在路径C:/coverage/Homo_sapiens.sort.add_exon1_coverage.txt,欲提取Homo_sapiens.sort.add_exon1_coverage.t ...
- ES6优缺点
看了一篇ES6语法示例,觉得还可以 here ES6是新一版的标准,对语言有扩展,添加了新的属性与方法.这一标准虽然现在还要用babel来做浏览器支持(将ES6编译成ES5才能被浏览器支持),但是未来 ...
- python nmap
#!/usr/bin/env python# -*- coding: utf-8 -*-import sysimport nmap scan_row = []input_data = input('P ...
- 如何解决串session:
在IE快捷方式上点击鼠标右键>属性>快捷方式>目标:"C:\Program Files\Internet Explorer\iexplore.exe" -nome ...
- mybatis下载地址(所有版本)
https://github.com/mybatis/mybatis-3/releases,这个github里面几乎包含了所有的没有batis
- linux ssh 报错failed - POSSIBLE BREAK-IN ATTEMPT
linux ssh 报错failed - POSSIBLE BREAK-IN ATTEMPT 问题故障: 今天在新租的虚拟机上,发现ssh登陆机器的时候报错,如下: [root@pictures_ne ...
- .gitignore无效的原因
有时候,我们编写gitinore后发现文件还是没有被忽略,这是什么原因呢? 熟知git的老鸟们可能已经知道,因为这个文件在之前已经被追踪了,如果想忽略已经被追踪的文件我们需要把这个追踪去除. 对所有文 ...
- python IDLE颜色设置
相信刚学习python的朋友们,都还是挺喜欢python自带的IDLE,但是白的代码背景色以及其它的代码色如何更改呢? Step1:找到config-Highlight.cfg文件,win在C:\Us ...