当前位置: 移动技术网 > IT编程>脚本编程>Python > 4.python读写csv文件

4.python读写csv文件

2019年08月13日  | 移动技术网IT编程  | 我要评论

sd001,kxsqw,电脑虚拟内存怎么设置

1.爬取豆瓣top250书籍

import requests
import json
import csv
from bs4 import beautifulsoup

books = []
def book_name(url): res = requests.get(url) html = res.text soup = beautifulsoup(html, 'html.parser') items = soup.find(class_="grid-16-8 clearfix").find(class_="indent").find_all('table') for i in items: book = [] title = i.find(class_="pl2").find('a') book.append('《' + title.text.replace(' ', '').replace('\n', '') + '》') star = i.find(class_="star clearfix").find(class_="rating_nums") book.append(star.text + '分') try: brief = i.find(class_="quote").find(class_="inq") except attributeerror: book.append('”暂无简介“') else: book.append(brief.text) link = i.find(class_="pl2").find('a')['href'] book.append(link) global books books.append(book) print(book) try: next = soup.find(class_="paginator").find(class_="next").find('a')['href'] # 翻到最后一页 except typeerror: return 0 else: return next next = 'https://book.douban.com/top250?start=0&filter=' count = 0 while next != 0: count += 1 next = book_name(next) print('-----------以上是第' + str(count) + '页的内容-----------') csv_file = open('d:/top250_books.csv', 'w', newline='', encoding='utf-8') w = csv.writer(csv_file) w.writerow(['书名', '评分', '简介', '链接']) for b in books: w.writerow(b)

结果

2.把评分为9.0的书籍保存到book_out.csv文件中

'''
1.爬取豆瓣评分排行前250本书,保存为top250.csv
2.读取top250.csv文件,把评分为9.0以上的书籍保存到另外一个csv文件中
'''

import csv

#打开的时候必须用encoding='utf-8',否则报错
with open('top250.csv', encoding='utf-8') as rf:
    reader = csv.reader(rf)
    #读取头部
    headers = next(reader)
    with open('books_out.csv', 'w', encoding='utf-8') as wf:
        writer = csv.writer(wf)
        #把头部信息写进去
        writer.writerow(headers)

        for book in reader:
            #获取评分
            score = book[1]
            #把评分大于9.0的过滤出来
            if score and float(score) >= 9.0:
                writer.writerow(book)

 

如对本文有疑问,请在下面进行留言讨论,广大热心网友会与你互动!! 点击进行留言回复

相关文章:

验证码:
移动技术网