csv模块简单使用

Posted 2020-09-17 Braveliberty

json是一种嵌套了列表与字典的格式，json包可以读取返回的json格式，json.load(html返回的对象)

csv模块，用来操作csv文件，

 1 import csv
 2 #from os import open
 3 
 4 csvFile = open("../files/test.csv", ‘w+‘, newline=‘‘)
 5 try:
 6     writer = csv.writer(csvFile)
 7     writer.writerow((‘number‘, ‘number plus 2‘, ‘number times 2‘))
 8     for i in range(10):
 9         writer.writerow( (i, i+2, i*2))
10 finally:
11     csvFile.close()

爬取一个页面上的表格

import csv
from urllib.request import urlopen
from bs4 import BeautifulSoup

html = urlopen("http://en.wikipedia.org/wiki/Comparison_of_text_editors")
bsObj = BeautifulSoup(html, "html.parser")
#The main comparison table is currently the first table on the page
table = bsObj.findAll("table",{"class":"wikitable"})[0]
rows = table.findAll("tr")

csvFile = open("files/editors.csv", ‘wt‘, newline=‘‘, encoding=‘utf-8‘)
writer = csv.writer(csvFile)
try:
    for row in rows:
        csvRow = []
        for cell in row.findAll([‘td‘, ‘th‘]):
            csvRow.append(cell.get_text())
        writer.writerow(csvRow)
finally:
    csvFile.close()