京东热水器评论情感分析：爬取信息

头像
HH丶丶
    阅读 12 分钟

    爬取目标

      本文的目标是爬取京东商城美的电热水器的品名、价格、评论数、好评率、差评率、中评率、标签、评论、评论时间、昵称、购买时间。

    爬取过程

    import requests
from bs4 import BeautifulSoup
import json
import re
import pymysql
import random
from multiprocessing import Pool

connection = pymysql.connect('localhost','root','0102003','spider')
cursor = connection.cursor()

      首先导入相关的包，并连接到本地的MySQL数据库，以便将爬取数据存入数据库。

    requests.DEFAULT_RETRIES = 5
uas = [ 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1',
        'Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
        'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6',
        'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5',
        'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
        'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3',
        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
        'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24']
def get_html(url):
    """
    用于获取html
    :param url: 网站的url地址
    :return: html
    """
    ua = random.choice(uas)
    head = {'user-agent': ua,
            'authority': 'item.jd.com',
            'method': ' GET',
            'path': '/1106432.',
            'scheme': 'https'}
    try:
        r = requests.get(url, head)
        return r.text
    except Exception as e:
        print(e，r.status_code)
        get_html(url)

      get_html函数用于发送请求并获取response，其中，使用random模块的random.choice()随机选取user-agent，try-except用于捕捉异常并打印异常类型和异常状态码。由于在使用过程中出现502异常，因此执行重复操作。

    def get_detail_urls():
    """
    获取所有美的热水器的详情页url
    :return:
    """
    detail_url_list = []
    for i in range(1, 14):
        url = 'https://list.jd.com/list.html?cat=737,13297,13690&ev=exbrand%5F12380&page={}&' \
          'sort=sort_totalsales15_desc&trans=1&JL=6_0_0#J_main'.format(i)
        soup = BeautifulSoup(get_html(url), 'lxml')
        for j in range(1, len(soup.select('#plist > ul > li'))+1):
            url = "https:" + soup.select('#plist > ul > li:nth-child({}) > div > div.p-name > a'.format(j))[0]\
            .attrs['href']
            name = soup.select('#plist > ul > li:nth-child(1) > div > div.p-name > a > em')[0].get_text().strip()
            detail_url_list.append((url, name))

    return detail_url_list

      get_detail_urls()原本是想获取商品详情页链接，然后在详情页获取相关数据，但是由于大多详情页数据是通过js加载的，无法直接从html网页获得，而且，获取详情页需要模拟登陆。因此，get_detail_urls()实际上获取了商品名称和url，其中url中有用是商品id信息，以此跳过对详情页的访问。

    def save_to_sql(l):

    sql = "insert into media values {}".format(tuple(l))
    try:
        cursor.execute(sql)
        connection.commit()
    except Exception as e:
        print(e)

      用于将数据插入MySQL数据库中。

    def get_info(url, title):

    id = url.split('/')[-1].split('.')[0]  # 获取商品id
    price_url = 'https://p.3.cn/prices/mgets?skuIds=J_' + id
    comment_info_url = 'https://club.jd.com/comment/productCommentSummaries.action?referenceIds={}'.format(id)
    comment_tag_url = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&' \
                      'productId={}&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&fold=1'.format(id)
    comment_info = json.loads(get_html(comment_info_url)).get('CommentsCount')[0]
    r = re.compile(".*?\((.*)\)")
    comment_tag = json.loads(r.findall(get_html(comment_tag_url))[0])

    tag = []  # 评价标签
    for i in comment_tag.get('hotCommentTagStatistics'):
        tag.append(i.get('name') + "("+str(i.get('count'))+ ")")
    tag = str(tag)
    price = float(json.loads(get_html(price_url))[0].get('p'))  # 商品价格
    CommentCount = comment_info.get('CommentCount')  # 评价总数
    GoodRate = comment_info.get('GoodRate')  # 好评率
    PoorRate = comment_info.get('PoorRate')  # 差评率
    GeneralRate = comment_info.get('GeneralRate')  # 中评率
    name = title

    out = False
    for i in range(100):

        comment_url = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&' \
                      'productId={}&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&fold=1'.format(id, i)
        r = re.compile(".*?\((.*)\);")
        try:
            comment = json.loads(r.findall(get_html(comment_url))[0]).get('comments')
        except Exception as e:
            print(id, i)
            print(e)
            break

        for j in range(10):
            try:
                com = comment[j].get('content')
            except IndexError as e:
                print(e)
                print(id, i, j)
                out = True
                break
            except TypeError as e:
                print(e)
                print(id, i, j)
                break
            comment_time = comment[j].get('creationTime')
            color = comment[j].get('productColor')
            bought_time = comment[j].get('referenceTime')
            nickname = comment[j].get('nickname')
            l = [name, price, CommentCount, GoodRate, GeneralRate, PoorRate,
                      tag, com, comment_time, nickname, bought_time]
            save_to_sql(l)
        if out:
            break

      获取某型号热水器的各种信息。
      首先，使用url获取商品的id，用于请求价格、评论等信息。price_url是使用商品id构建的一个返回包含商品价格的json文件的url，使用json.loads()将json文件解码成python的字典，然后获取价格信息。
      comment_info_url是一个包含商品评价的聚合统计量（如评论数、好评率等）的json文件，这些信息也可以在之后的comment_tag_url中获取。
      comment_tag_url是comment_url的第一页，京东只保存了商品的最多100页评论信息，每页最多十条评论，对页码循环并构建url。由于返回的文件并不是标准的json格式文件，因此，需要使用正则表达式获取标准的json信息。当评论数较少，循环页码超出时跳出循环。对每一页评论信息循环获取每条评论内容，同理，当不足十条时，跳出循环。将所需信息存入列表后插入MySQL数据库。

    def job(z):
    return get_info(z[0], z[1])


def main():
    urls = get_detail_urls()
    print(len(urls))
    pool = Pool()
    pool.map(job, urls)
    pool.close()
    pool.join()

      main函数只需串联起来即可，使用multiprocessing的Pool实现多进程爬取，代码综合如下：

    import requests
from bs4 import BeautifulSoup
import json
import re
import pymysql
import random
from multiprocessing import Pool

connection = pymysql.connect('localhost','root','0102003','spider')
cursor = connection.cursor()

requests.DEFAULT_RETRIES = 5
uas = ["Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"]
def get_html(url):
    """
    用于获取html
    :param url: 网站的url地址
    :return: html
    """
    ua = random.choice(uas)
    head = {"user-agent": ua,
            'authority': 'item.jd.com',
            'method': ' GET',
            'path': '/1106432.',
            'scheme': 'https'}
    try:
        r = requests.get(url, head)
        return r.text
    except Exception as e:
        print(e)
        get_html(url)


def get_detail_urls():
    """
    获取所有美的热水器的详情页url
    :return:
    """
    detail_url_list = []
    for i in range(1, 14):
        url = 'https://list.jd.com/list.html?cat=737,13297,13690&ev=exbrand%5F12380&page={}&' \
          'sort=sort_totalsales15_desc&trans=1&JL=6_0_0#J_main'.format(i)
        soup = BeautifulSoup(get_html(url), 'lxml')
        for j in range(1, len(soup.select('#plist > ul > li'))+1):
            url = "https:" + soup.select('#plist > ul > li:nth-child({}) > div > div.p-name > a'.format(j))[0]\
            .attrs['href']
            name = soup.select('#plist > ul > li:nth-child(1) > div > div.p-name > a > em')[0].get_text().strip()
            detail_url_list.append((url, name))

    return detail_url_list


def save_to_sql(l):

    sql = "insert into media values {}".format(tuple(l))
    try:
        cursor.execute(sql)
        connection.commit()
    except Exception as e:
        print(e)


def get_info(url, title):

    id = url.split('/')[-1].split('.')[0]  # 获取商品id
    price_url = 'https://p.3.cn/prices/mgets?skuIds=J_' + id
    comment_info_url = 'https://club.jd.com/comment/productCommentSummaries.action?referenceIds={}'.format(id)
    comment_tag_url = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&' \
                      'productId={}&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&fold=1'.format(id)
    comment_info = json.loads(get_html(comment_info_url)).get('CommentsCount')[0]
    r = re.compile(".*?\((.*)\)")
    comment_tag = json.loads(r.findall(get_html(comment_tag_url))[0])

    tag = []  # 评价标签
    for i in comment_tag.get('hotCommentTagStatistics'):
        tag.append(i.get('name') + "("+str(i.get('count'))+ ")")
    tag = str(tag)
    price = float(json.loads(get_html(price_url))[0].get('p'))  # 商品价格
    CommentCount = comment_info.get('CommentCount')  # 评价总数
    GoodRate = comment_info.get('GoodRate')  # 好评率
    PoorRate = comment_info.get('PoorRate')  # 差评率
    GeneralRate = comment_info.get('GeneralRate')  # 中评率
    name = title

    out = False
    for i in range(100):

        comment_url = 'https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&' \
                      'productId={}&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&fold=1'.format(id, i)
        r = re.compile(".*?\((.*)\);")
        try:
            comment = json.loads(r.findall(get_html(comment_url))[0]).get('comments')
        except Exception as e:
            print(id, i)
            print(e)
            break

        for j in range(10):
            try:
                com = comment[j].get('content')
            except IndexError as e:
                print(e)
                print(id, i, j)
                out = True
                break
            except TypeError as e:
                print(e)
                print(id, i, j)
                break
            comment_time = comment[j].get('creationTime')
            color = comment[j].get('productColor')
            bought_time = comment[j].get('referenceTime')
            nickname = comment[j].get('nickname')
            l = [name, price, CommentCount, GoodRate, GeneralRate, PoorRate,
                      tag, com, comment_time, nickname, bought_time]
            save_to_sql(l)
        if out:
            break


def job(z):
    return get_info(z[0], z[1])


def main():
    urls = get_detail_urls()
    print(len(urls))
    pool = Pool()
    pool.map(job, urls)
    pool.close()
    pool.join()


if __name__ == '__main__':
    main()
    网页爬虫
    HH丶丶
    29 声望8 粉丝
    « 上一篇
    关联分析：Apriori算法的python实现
    下一篇 »
    机器学习基础之决策树

    引用和评论

    推荐阅读
    头像
    机器学习基础之模型集成

    HH丶丶阅读 3.3k

    0 条评论
    得票最新