用 BeautifulSoup爬取58商品信息

最近对Python爬虫比较迷恋，看了些爬虫相关的教程

于是乎跟着一起爬取了58上面的一些商品信息，并存入到xlsx文件中，并通过xlsxwirter的方法给表格设置了一些格式。好了，直接贴代码吧~

#coding:utf-8
from bs4 import BeautifulSoup
import requests
import sys
import xlsxwriter
import re
reload(sys)
sys.setdefaultencoding('utf8')

def get_links_from(urls,who_sell=0,page=1):
    list_view = 'http://bj.58.com/haidian/pbdn/{}/pn{}/'.format(str(who_sell), str(page))
    web_data = requests.get(list_view)
    soup = BeautifulSoup(web_data.text, "lxml")
    for url in soup.select('td.t a.t'):
        url = url.get('href').split('?')[0]
        if url.find('zhuanzhuan.58.com') != -1:
            urls.append(url)
    is_next = soup.select('.next')
    if is_next:                                             #如果存在下一页，继续获取url并保存到urls
        get_links_from(urls,who_sell,page+1)
    return  urls

def get_views_from(url):
    id = url.split('/')[-1].strip('z.shtml')
    api = 'http://jst1.58.com/counter?infoid={}'.format(id)
    js = requests.get(api)
    view = js.text.split('=')[-1]
    return view

def get_item_info(who_sell):
    datas = []
    urls = []
    urls = get_links_from(urls,who_sell,1)

    workbook = xlsxwriter.Workbook(u'F:/Python27/magua/download/二手平板.xlsx')
    worksheet = workbook.add_worksheet('haidian')
    format = workbook.add_format({'bold':True, 'font_color': 'B452CD', 'font_size': 16, 'align':'center', 'bg_color':'FFA54F'})
    worksheet.set_row(0, 20)            #设置第1行的单元格高度
    worksheet.set_column('A:A', 100)    #设置第A列的单元格长度
    worksheet.set_column('C:C', 15)     #设置第C列的单元格长度
    worksheet.set_column('D:D', 15)     #设置第D列的单元格长度
    worksheet.set_column('E:E', 15)     #设置第E列的单元格长度
    worksheet.write(0, 0, '标题', format)
    worksheet.write(0, 1, '价格', format)
    worksheet.write(0, 2, '区域', format)
    worksheet.write(0, 3, '个人/商家', format)
    worksheet.write(0, 4, '浏览量', format)
    # workbook.close()
    # return

    row_num = 1
    for url in urls:
        web_data = requests.get(url)
        soup = BeautifulSoup(web_data.text, "lxml")
        data = {
            'title':soup.title.text.strip(),    #strip 去掉字符串中的换行、制表符
            'price':soup.select('.price_now i')[0].text,    # #代表id
            'area':soup.select('.palce_li i')[0].text,
            'cate':u'个人' if who_sell ==0 else u'商家',
            'view':soup.select('.look_time')[0].text.split('次')[0],
            # 'views':get_views_from(url),
        }
        # datas.append(data)

        if row_num%2:
            format_ = workbook.add_format({'bg_color': 'FFEC8B', 'font_size': 12})
        else:
            format_ = workbook.add_format({'bg_color': 'FFDAB9', 'font_size': 12})
        #write the data into .xlsx file
        worksheet.write(row_num, 0, data['title'], format_)
        worksheet.write(row_num, 1, data['price'], format_)
        worksheet.write(row_num, 2, data['area'], format_)
        worksheet.write(row_num, 3, data['cate'], format_)
        worksheet.write(row_num, 4, data['view'], format_)
        row_num = row_num + 1
    workbook.close()

    '''
    for item in datas:
        print repr(item).decode("unicode-escape")
        # print item
    print "total: %d" % len(datas)
    '''

get_item_info(0)    #参数 0为个人，1为商家

在这过程中有点不明白的地方就是xlsxwriter.Workbook 方法在创建xlsx文件的时候，必须要绝对路径才能成功，看官方文档也没找到问题的原因

最后抓取信息所生成的表格文件截图