常用数据存储的介绍和使用

## 文本存储；简单实例，爬取知乎话题、答者和回答内容保存到txt文件中
from pyquery import PyQuery as pq
import requests

url = ‘https://www.zhihu.com/explore‘
headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36‘
}
html = requests.get(url=url, headers=headers).text

doc = pq(html)
items = doc.find(‘.ExploreCollectionCard-contentItem‘).items()
for item in items:
    question = item(‘.ExploreCollectionCard-contentTitle‘).text()
    author = item(‘.ExploreCollectionCard-contentExcerpt‘).text().split(‘：‘)[0]
    answer = ‘‘.join(item(‘.ExploreCollectionCard-contentExcerpt‘).text().split(‘：‘)[1:])
    with open(‘zhihu_explore.txt‘, ‘a‘, encoding=‘utf-8‘) as f:
        f.write(‘\n‘.join([question, author, answer]))
        f.write(‘\n‘ + ‘=‘ * 50 + ‘\n‘)

## JSON文件存储
## JSON中两种常用的类型：对象和数组，可以理解为python中的字典和列表，两者可以互相嵌套
## 读取JSON，JSON字符串的数据一定要用双引号表示，否则会解析失败
import json

str = ‘‘‘
[
{"name":"dmr", "age":"25", "score":"80"},
{"name":"asx", "age":"23", "score":"81"}
]
‘‘‘
print(type(str))
str = json.loads(str)
print(type(str))
# 读取value，通过字典的get方法，当key不存在时，不会报错，会返回None
print(str[0][‘name‘])
print(str[0].get(‘age‘))

‘‘‘
输出内容：
<class ‘str‘>
<class ‘list‘>
dmr
25
‘‘‘


## 写入JSON，字典转换成JSON字符串格式，json会自动识别格式并修正转换，如单引号改为双引号
import json

d = {
    ‘name‘: [‘dmr‘, ‘asx‘, ‘逗比‘],
    ‘age‘: ‘25‘,
}
# 把特定格式数据转换成JSON格式
data_json = json.dumps(d)
# indent，指定缩进字符量
data_json2 = json.dumps(d, indent=2)
# ensure_ascii使内容可以以中文显示
data_json3 = json.dumps(d, indent=2, ensure_ascii=False)
print(data_json)
print(data_json2)
print(data_json3)
# 保存JSON内容到文件中
with open(‘data.json‘, ‘w‘, encoding=‘utf-8‘) as f:
    f.write(‘\n‘.join([data_json, data_json2, data_json3]))

‘‘‘
输出内容：
{"name": ["dmr", "asx", "\u9017\u6bd4"], "age": "25"}
{
  "name": [
    "dmr",
    "asx",
    "\u9017\u6bd4"
  ],
  "age": "25"
}
{
  "name": [
    "dmr",
    "asx",
    "逗比"
  ],
  "age": "25"
}
‘‘‘

## CSV文件，以纯文本形式存储表格数据
## 写入
import csv

with open(‘data.csv‘, ‘w‘) as csvf:
    # 获得文件句柄
    writer = csv.writer(csvf)
    # 获得文件句柄并指定分隔符
    writer2 = csv.writer(csvf, delimiter=‘ ‘)
    # 写入行内容
    writer.writerow([‘id‘, ‘name‘, ‘age‘])
    writer.writerow([‘0001‘, ‘dmr‘, ‘25‘])
    writer.writerow([‘0002‘, ‘asx‘, ‘23‘])
    writer.writerow([‘0003‘, ‘scy‘, ‘26‘])
    writer2.writerow([‘0004‘, ‘test‘, ‘22‘])
    writer2.writerow(‘=================================‘)
    # 写入多行
    writer2.writerows([[‘id‘, ‘name‘, ‘age‘], [‘0001‘, ‘dmr‘, ‘25‘], [‘0003‘, ‘scy‘, ‘26‘]])
    writer2.writerow(‘=================================‘)

    # 通过字典形式进行文件添加内容
    fieldnames = [‘id‘, ‘name‘, ‘age‘]
    writer3 = csv.DictWriter(csvf, fieldnames=fieldnames)
    # 生成fieldnames的首行
    writer3.writeheader()
    # 写入内容
    writer3.writerow({‘id‘: ‘0001‘, ‘name‘: ‘dmr‘, ‘age‘: ‘25‘})
    writer3.writerow({‘id‘: ‘0002‘, ‘name‘: ‘asx‘, ‘age‘: ‘23‘})
    writer3.writerow({‘id‘: ‘0003‘, ‘name‘: ‘scy‘, ‘age‘: ‘26‘})



## 读取
import csv

with open(‘data.csv‘, ‘r‘, encoding=‘utf-8‘) as csvf:
    reader = csv.reader(csvf)
    print(reader)
    for row in reader:
        print(row)


# 用pandas模块进行文件读取
import pandas as pd

data = pd.read_csv(‘data.csv‘)
print(data)