（四）爬取出版社信息并存储到Excel中

（一）安装xlsxwriter、xlrd模块

首先打开cmd，通过下列指令安装XlsxWriter（注意拼写）模块和xlrd模块

pip install Xlsxwriter

pip install xlrd

 

如果cmd下pip命令无法使用，则应在系统环境变量中添加python安装路径下的Script文件夹。

一台电脑若同时安装python 3.6.x 和 2.7.x版本，lib将会安装在3.6.x版本下。安装成功后，在Pycharm下的Settings - Project Interpreter可查看到安装的模块。

具体使用信息可参见https://xlsxwriter.readthedocs.io/getting_started.html

（二）爬取出版社信息（使用3.6.x版本）

import urllib.request
import re
import xlsxwriter
import xlrd
import os

def build_xls(name):
    i=1
    if os.path.exists(target_dir+name+'.xlsx'):
        while os.path.exists(target_dir+name+'(%s).xlsx' % i):
            i+=1
        path=target_dir+name+'(%s).xlsx'% i
    else:
        path=target_dir+name+'.xlsx'
    return xlsxwriter.Workbook(path)
def build_sheet(f,name):
    return f.add_worksheet(name)
def open_xls(dir):
    try:
        return xlrd.open_workbook(dir)
    except Exception as err:
        print(err)

target_dir=r'c:/backup/'

data=urllib.request.urlopen("https://read.douban.com/provider/all").read().decode("utf-8") 
#注意需要decode为utf-8格式，否则无法使用re模块进行正则表达式匹配
#print(len(data))
pat='<div class="name">(.*?)</div>'
ans=re.compile(pat).findall(data)

f=build_xls('book')
worksheet=build_sheet(f,'publisher')
worksheet.write(0,0,r"出版社信息",f.add_format({'bold':1}))
row=1
for i in range(len(ans)):
    worksheet.write(row,0,ans[i])
    row+=1
f.close()

 

（三）爬取出版社信息和作品数量，并存入不同的选项卡

import urllib.request
import re
import xlsxwriter
import xlrd
import os

def build_xls(name):
    i=1
    if os.path.exists(target_dir+name+'.xlsx'):
        while os.path.exists(target_dir+name+'(%s).xlsx' % i):
            i+=1
        path=target_dir+name+'(%s).xlsx'% i
    else:
        path=target_dir+name+'.xlsx'
    return xlsxwriter.Workbook(path)
def build_sheet(f,name):
    return f.add_worksheet(name)
def open_xls(dir):
    try:
        return xlrd.open_workbook(dir)
    except Exception as err:
        print(err)

target_dir=r'c:/backup/'

data=urllib.request.urlopen("https://read.douban.com/provider/all").read().decode("utf-8")
#print(len(data))
pat='<div class="name">(.*?)</div>'
pat2='<div class="works-num">.*?(\d+).*?</div>'
ans=re.compile(pat).findall(data)
ans2=re.compile(pat2).findall(data)
f=build_xls('book')
worksheet=build_sheet(f,'publisher')
worksheet.write(0,0,r"出版社信息",f.add_format({'bold':1}))
row=1
for i in range(len(ans)):
    worksheet.write(row,0,ans[i])
    row+=1

worksheet=build_sheet(f,'publisher&name')
worksheet.write(0,0,r"出版社信息",f.add_format({'bold':1}))
worksheet.write(0,1,r"作品数量",f.add_format({'bold':1}))
row=1
for i in range(len(ans2)):
    worksheet.write(row,0,ans[i])
    worksheet.write(row,1,ans2[i])
    row+=1

f.close()

 

转载于:https://www.cnblogs.com/yitiaoluyu/p/7720022.html