python3.7 糗事第一页写入xls

问题描述： 2021年7月21日16:5:57 试着爬取了糗事第一页的 (1： 标题；2： 笑的人数； 3 ： 评论人数； 4： 作者)

# -*- coding=utf-8 -*-

import urllib.request
from lxml import etree
import json
import xlwt


class EmbarrassmentEncyclopedia(object):
    def __init__(self, url):
        self.url = url
        self.header = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36",
            "Cookie": '_qqq_uuid_="2|1:0|10:1626351094|10:_qqq_uuid_|56:ZGI3N2NkN2JhOWIwNGY3YTYwYmFjYWVlMGFkNmQ0Y2FkNmFiZTYyYg==|2646ac3ceb6bd51c14ab695b46705339eb888581145dbdb8d49b67d2bd162877";'
        }

    # 目标， 拿到， 1： 标题；2： 好笑； 3： 评论数 , 4 作者
    def get_html(self):
        try:
            req = urllib.request.Request(url, headers=self.header)
            resp = urllib.request.urlopen(req).read().decode("utf-8")
            html = etree.HTML(str(resp))
            print("返回类型是： " + str(type(html)))
            result = html.xpath('//div[@class="recommend-article"]/ul/li[contains(@class, "item")]')
            print(str(len(result)))

            if len(result) > 0:
                self.get_attributes(result)
            else:
                print("html.xpath 匹配到的内容为空")

        except Exception as e:
            print(e)

    # 对匹配到的元素进行分割
    def get_attributes(self, ele):
        try:
            print(type(ele))        # 类型
            print(ele[0].attrib)    # 它里面的属性

            # 下面测试拿值
            '''
            test_title = ele[1].xpath('.//a[contains(@class, "recmd-content")]/text()')
            test_laughter_nmb = ele[1].xpath('.//div[contains(@class, "recmd-num")]/span[1]/text()')
            test_comments_nmb = ele[1].xpath('.//div[contains(@class, "recmd-num")]/span[4]/text()')
            test_auth = ele[1].xpath('.//span[contains(@class, "recmd-name")]/text()')
            print("----------")
            print(type(test_title))
            print(test_title)
            print("----------")
            print(int(test_laughter_nmb[0]))
            print("----------")
            print(len(test_comments_nmb))
            if len(test_comments_nmb) == 0:
                print("没值")
            print("----------")
            print(test_auth)
            '''

            # 由上面测试值可知，需要拿的数据用 for 循环 1： 标题；2： 好笑； 3： 评论数 , 4 作者
            items = []
            for attrib in ele:
                embarrassment_title = attrib.xpath('.//a[contains(@class, "recmd-content")]/text()')[0]
                embarrassment_laughter_nmb = attrib.xpath('.//div[contains(@class, "recmd-num")]/span[1]/text()')   # 可能返回空值
                embarrassment_comments_nmb = attrib.xpath('.//div[contains(@class, "recmd-num")]/span[4]/text()')   # 可能返回空值
                embarrassment_auth = attrib.xpath('.//span[contains(@class, "recmd-name")]/text()')[0]

                embarrassment_laughter_nmb = judge_zero(embarrassment_laughter_nmb)
                embarrassment_comments_nmb = judge_zero(embarrassment_comments_nmb)

                item = {
                    "title": embarrassment_title,
                    "laughter_nmb": embarrassment_laughter_nmb,
                    "comments_nmb": embarrassment_comments_nmb,
                    "auth": embarrassment_auth
                }
                items.append(item)
                print("添加数据" + str(item) + "完成... ...")

            deal_json(items)

        except Exception as e:
            print(e)

    def get_started(self):
        print("开始访问目标网站：")
        self.get_html()


# 返 0 判断
def judge_zero(nmb):
    if len(nmb) == 0:
        return 0
    else:
        return int(nmb[0])


# 处理 JSON 数据
def deal_json(json_data):
    print(json_data)
    print(type(json_data))  # json_data 是 list 列表
    # json.dumps 先把列表转成字符串，再用， json.loads() 把字符串转成 json 数据( dict )
    print(type(json.dumps(json_data)))  # json.dumps 把它变成 str 类型
    data = json.loads(json.dumps(json_data))    # 打印出来 是 list 类型
    write_xls(data)


# 写入 xls
def write_xls(json_data):
    xls_workbook = xlwt.Workbook()
    xls_worksheet = xls_workbook.add_sheet("糗事百科第一页的简单数据")
    json_data_len = len(json_data)
    xls_style = set_xls_style(xls_worksheet, 4, json_data_len)

    titles = ['标题', '笑的人数', '评论人数', '作者']
    titles_len = len(titles)
    for i in range(titles_len):
        xls_worksheet.write(0, i, titles[i], xls_style)

    xls_style_align_center = set_xls_center(xls_worksheet)

    for j in range(json_data_len):
        xls_worksheet.write(j + 1, 0, json_data[j]["title"], xls_style_align_center)
        xls_worksheet.write(j + 1, 1, json_data[j]["laughter_nmb"], xls_style_align_center)
        xls_worksheet.write(j + 1, 2, json_data[j]['comments_nmb'], xls_style_align_center)
        xls_worksheet.write(j + 1, 3, json_data[j]['auth'], xls_style_align_center)
        print("数据写入了 " + str(j + 1) + "条了")

    xls_workbook.save("./08Qiushi.xlsx")


def set_xls_style(sheet, col_nmb, row):
    xls_style = xlwt.XFStyle()
    xls_font = xlwt.Font()
    xls_font.name = u'仿宋'
    xls_font.bold = True
    xls_font.height = 240
    xls_style.font = xls_font
    xls_alignment = xlwt.Alignment()
    xls_alignment.horz = xlwt.Alignment.HORZ_CENTER
    xls_alignment.vert = xlwt.Alignment.VERT_CENTER
    xls_style.alignment = xls_alignment

    for i in range(col_nmb + 1):
        sheet.col(i).width = 256 * 20

    font_height = xlwt.easyxf('font:height 300')
    for i in range(row + 1):                                # 先设置所有的行高，再对第一行的行高进行改变
        sheet.row(i).set_style(font_height)

    sheet.row(0).set_style(xlwt.easyxf('font:height 480'))  # 首行的高度
    return xls_style


def set_xls_center(worksheet):
    xls_center = xlwt.XFStyle()
    xls_alignment = xlwt.Alignment()
    xls_alignment.horz = xlwt.Alignment.HORZ_CENTER
    xls_alignment.vert = xlwt.Alignment.VERT_CENTER
    xls_center.alignment = xls_alignment
    return xls_center


if __name__ == '__main__':
    url = "https://www.qiushibaike.com/8hr/page/1/"
    embarrassments_encyclopedia = EmbarrassmentEncyclopedia(url)
    embarrassments_encyclopedia.get_started()

问题解决：