【爬虫实例3】异步爬取大量数据

1、导入模块

import requests
import csv
from concurrent.futures import ThreadPoolExecutor

2、先获取第一个页面的内容

分析得到该页面的数据是从getPriceData.html页面获取,并保存在csv文件中

得到url地址后,提取第一个页面内容

def download(url, num):
    resp = requests.post(url).json()
    for i in resp[\'list\']:
        temp = [i[\'prodName\'], i[\'lowPrice\'], i[\'highPrice\'], i[\'avgPrice\'], i[\'place\'], i[\'unitInfo\'], i[\'pubDate\']]
        csvwrite.writerow(temp)
   


if __name__ == \"__main__\":
    url = \'http://www.xinfadi.com.cn/getPriceData.html\'
    download(url)
    print(\'success\')

** 此为第一个页面信息提取:**

3、获取更多的信息

分析页面数据显示规律,请求地址时页面携带页码和需要显示数据的条数,一共17362页,每页20条数据

设置100个线程提取17362页数据,同时每次请求时传入页码

def download(url, num):
    data = {
        \"limit\": 20,
        \"current\": num
    }
    resp = requests.post(url, data=data).json()
    for i in resp[\'list\']:
        temp = [i[\'prodName\'], i[\'lowPrice\'], i[\'highPrice\'], i[\'avgPrice\'], i[\'place\'], i[\'unitInfo\'], i[\'pubDate\']]
        csvwrite.writerow(temp)
    print(f\'{num}页提取完成\')


if __name__ == \"__main__\":
    url = \'http://www.xinfadi.com.cn/getPriceData.html\'
    # 设置100个线程
    with ThreadPoolExecutor(100) as t:
        for i in range(1, 17363):
            t.submit(download(url, i))
    print(\'success\')

4、完整代码

4、完整代码

# 1、提取单页面

import requests
import csv
from concurrent.futures import ThreadPoolExecutor

f = open(\"data.csv\", mode=\"w\", encoding=\"utf-8\")
csvwrite = csv.writer(f)


def download(url, num):
    data = {
        \"limit\": 20,
        \"current\": num
    }
    resp = requests.post(url, data=data).json()
    for i in resp[\'list\']:
        temp = [i[\'prodName\'], i[\'lowPrice\'], i[\'highPrice\'], i[\'avgPrice\'], i[\'place\'], i[\'unitInfo\'], i[\'pubDate\']]
        csvwrite.writerow(temp)
    print(f\'{num}页提取完成\')


if __name__ == \"__main__\":
    url = \'http://www.xinfadi.com.cn/getPriceData.html\'
    # 设置100个线程
    with ThreadPoolExecutor(100) as t:
        for i in range(1, 17363):
            t.submit(download(url, i))
    print(\'success\')

以下为第1页~第199页数据:

来源：https://www.cnblogs.com/nnguhx/p/16585560.html
本站部分图文来源于网络，如有侵权请联系删除。