Python爬取京东评论（多线程+队列+bs4+pymysql）

1、 概述

本博客纯属原创，如有转载，请注明作者
运行环境：python3.5

所需模块：bs4 ,queue.thread,pymysql,requests，大家如果想运行此代码，只需要将我标粗的部分修改即可。

2、具体内容

2、1导入具体模块

###导入具体模块
import requests
from  bs4 import BeautifulSoup
import re
from collections import deque
import sys
import numpy as np
import jieba
import threading
from threading import current_thread,Lock
from time import ctime ,sleep
import pymysql
import json
import urllib
import math
import queue

2、2定义线程类

class MyThread(threading.Thread):
    def __init__(self, funcs, args, name=''):
        threading.Thread.__init__(self)
        self.funcs = funcs
        self.name = name
        self.args = args

    def run(self):
        self.funcs(*self.args)

2、3接下来就是重点了

###接下来就是爬取网页了
def getContent(que):
    while que:
        try:
            url = que.popleft()
            print('正在爬的线程是'+current_thread().name+"爬的是"+url)
            **headers** = {
                'Accept': 'text / html, application / xhtml + xml, image / jxr, * / *',
                'Accept - Encoding': 'gzip, deflate',
                'Accept - Language': 'zh - Hans - CN, zh - Hans;q = 0.5',
                'User - Agent': 'Mozilla / 5.0(Windows NT 10.0; Win64;x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome/51.0.2704.79 Safari/ 537.36Edge/14.14393',
                'Connection': 'Keep - Alive'
           }
            req = requests.get(url, headers=headers)
            req.encoding = 'gbk'
            res = req.text
            bs = BeautifulSoup(res)

            bs = bs.find_all('div', class_='i-item')
            total = []
            for i in bs:
                reg1 = i.find('dd')
                reg2 = i.find('span', class_=re.compile(r'^sta'))
                scores = reg2.get('class')
                scores = ''.join(scores)
                scores = str(scores)

                if scores == 'starsa5' or scores == 'starsa4' or scores == 'starsa3':
                    j = 1
                #
                #     j=1
                #
                if scores == 'starsa2' or scores == 'starsa1' or scores == 'starsa0':
                    j = 0

                reg3 = re.compile("<[^>]*>")
                content = reg3.sub('', reg1.prettify())
                print(content)
                total.append((content, scores, j))
                **db = pymysql.connect('localhost', 'root', '**********', 'test')**
                db.encoding = 'utf-8'
                cursor = db.cursor()
                cursor.execute('set names utf8')
                sql = "INSERT INTO newjd (comment,scores ) VALUES ('%s','%s') "
                sql2 = "INSERT INTO test1 (title) VALUES ('%s') "
                cursor.execute(sql % (content, j))
                db.commit()
                cursor.close()
                db.close()
            sleep(3)
        except Exception:
            print('运行出错')

2、4运行

###在这里我用了四个线程
def main():
    que = deque()
    visited = set()
    id = [549056]####可自行选择商品id
    commentpeypage = 30

    for i in id:

        itemsummaryurl = 'http://club.jd.com/ProductPageService.aspx?method=GetCommentSummaryBySkuId&referenceId=' + str(
            i)
        itemsummaryresponse = urllib.request.urlopen(itemsummaryurl)

        itemsummaryjson_dict = json.loads(itemsummaryresponse.read().decode('utf-8'))

        commentrange = int(math.ceil(itemsummaryjson_dict.get('CommentCount')) / commentpeypage)
        for j in range(commentrange):
            url = 'http://club.jd.com/review/' + str(i) + '-0-' + str(j) + '-0.html'
            que.append(url)
    thread=[]
    for i in range(4):
        t = MyThread(getContent, (que, ), name='thread' + str(i))
        thread.append(t)
    for i in range(4):
        thread[i].start()
    for i in range(4):
        thread[i].join()

if __name__ =='__main__':

    main()