爬虫之数据保存到txt文本中

本节为保存爬虫数据到txt文本中，还是以排行榜为例，上节可以看：爬虫之数据保存到csv，xlsx等Excel文件中

数据获取代码如下：

import requests
from fake_useragent import UserAgent
from lxml import html
import pandas as pd

etree = html.etree
from bs4 import BeautifulSoup

url = 'https://www.17k.com/top/refactor/top100/14_recommend/14_recommend_top_100_pc.html'

# 定义变量：URL 与 headers
headers = {'User-Agent': str(UserAgent().random)}
# 根据访问的网址为https选用“https”,选http用“http”
# proxies = {'协议': '协议://IP:端口号'}
ips = {"https": "https://58.20.232.245:9091"}
ip = {"http": "http://58.20.232.245:9091"}

get = requests.get(url, proxies=ip, headers=headers)
get.encoding = 'UTF-8'
soup = BeautifulSoup(get.text, 'lxml')
div = soup.find(name='div', attrs={'class': "TYPE"})
a = div.find_all(name='a')
table = list()
for i in a:
    table.append(i.string)

table0 = table[0::4]
for i in range(0, len(table0)):
    table0[i] = table0[i].replace('[', '').replace(']', '')
table1 = table[1::4]
table2 = table[2::4]
table3 = table[3::4]

数据保存到txt文本如下：

file = open('排行榜.txt', 'w', encoding='utf-8')
for i in range(0, len(table1)):
    file.write(f'书名：{table1[i]}\n')
    file.write(f'作者：{table3[i]}\n')
    file.write(f'类型：{table0[i]}\n')
    file.write(f'最新章节：{table2[i]}\n')
    file.write(f'{"=" * 30}\n')
file.close()
print('ok')

效果如下：

最终代码如下：

import requests
from fake_useragent import UserAgent
from lxml import html
import pandas as pd

etree = html.etree
from bs4 import BeautifulSoup

url = 'https://www.17k.com/top/refactor/top100/14_recommend/14_recommend_top_100_pc.html'

# 定义变量：URL 与 headers
headers = {'User-Agent': str(UserAgent().random)}
# 根据访问的网址为https选用“https”,选http用“http”
# proxies = {'协议': '协议://IP:端口号'}
ips = {"https": "https://58.20.232.245:9091"}
ip = {"http": "http://58.20.232.245:9091"}

get = requests.get(url, proxies=ip, headers=headers)
get.encoding = 'UTF-8'
soup = BeautifulSoup(get.text, 'lxml')
div = soup.find(name='div', attrs={'class': "TYPE"})
a = div.find_all(name='a')
table = list()
for i in a:
    table.append(i.string)

table0 = table[0::4]
for i in range(0, len(table0)):
    table0[i] = table0[i].replace('[', '').replace(']', '')
table1 = table[1::4]
table2 = table[2::4]
table3 = table[3::4]

file = open('排行榜.txt', 'w', encoding='utf-8')
for i in range(0, len(table1)):
    file.write(f'书名：{table1[i]}\n')
    file.write(f'作者：{table3[i]}\n')
    file.write(f'类型：{table0[i]}\n')
    file.write(f'最新章节：{table2[i]}\n')
    file.write(f'{"=" * 30}\n')
file.close()
print('ok')