Python爬虫数据存哪里|数据存储到文件的几种方式

import requests
from bs4 import BeautifulSoup

urls=['https://book.douban.com/subject/1200840/comments/?start={}&limit=20&status=P&sort=new_score'.format(str(i)) for i in range(0, 60, 20)] #通过观察的url翻页的规律，使用for循环得到3个链接，保存到urls列表中
print(urls)
dic_h = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"}
comments_list = [] #初始化用于保存短评的列表

for url in urls: #使用for循环分别获取每个页面的数据，保存到comments_list列表
    r = requests.get(url=url,headers = dic_h).text

    soup = BeautifulSoup(r, 'lxml')
    ul = soup.find('div',id="comments")
    lis= ul.find_all('p')

    list2 =[]
    for li in lis:
        list2.append(li.find('span').string)
    # print(list2)
    comments_list.extend(list2)
 print(comments_list)

with open('comments.txt', 'w', encoding='utf-8') as f: #使用with open()新建对象f
    # 将列表中的数据循环写入到文本文件中
    for i in comments_list:
        f.write(i+"\n") #写入数据

import csv

headers = ['No','name','age']
values = [
    ['01','zhangsan',18],
    ['02','lisi',19],
    ['03','wangwu',20]
]
with open('test1.csv','w',newline='') as fp:
    # 获取对象
    writer = csv.writer(fp)
    # 写入数据
    writer.writerow(headers) #写入表头
    writer.writerows(values) # 写入数据

import csv

headers = ['No','name','age']
values = [
    {"No":'01',"name":'zhangsan',"age":18},
    {"No":'02',"name":'lisi',"age":19},
    {"No":'03',"name":'wangwu',"age":20}]
with open('test.csv','w',newline='') as fp:
    dic_writer = csv.DictWriter(fp,headers)
    dic_writer.writeheader()# 写入表头
    dic_writer.writerows(values) #写入数据

import requests
import csv
from bs4 import BeautifulSoup
urls=['https://book.douban.com/subject/1200840/comments/?start={}&limit=20&status=P&sort=new_score'.format(str(i)) for i in range(0, 60, 20)] #通过观察的url翻页的规律，使用for循环得到5个链接，保存到urls列表中
print(urls)
dic_h = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"}
comments_list = [] #初始化用于保存短评的列表

for url in urls: #使用for循环分别获取每个页面的数据，保存到comments_list列表
    r = requests.get(url=url,headers = dic_h).text

    soup = BeautifulSoup(r, 'lxml')
    ul = soup.find('div',id="comments")
    lis= ul.find_all('p')

    list2 =[]
    for li in lis:
        list2.append(li.find('span').string)
    # print(list2)
    comments_list.extend(list2)

new_list = [[x] for x in comments_list] #列表生成器，将列表项转为子列表

with open("com11.csv", mode="w", newline="", encoding="utf-8") as f:
    csv_file = csv.writer(f) # 创建CSV文件写入对象
    for i in new_list:
        csv_file.writerow(i)

df = pd.DataFrame(comments_list) #把comments_list列表转换为pandas DataFrame
df.to_excel('comments.xlsx') #保存到excel表格
# df.to_csv('comments.csv')#保存在csv文件