Python爬虫使用示例-古诗词摘录

镜花照无眠2024-10-19 20:10

一、分析需求

目标地址：

https://www.sou-yun.cn/Query.aspx?type=poem&id=×××××

二、提取诗句

python 复制代码 
import os
import re
import requests
import parsel

#url ='https://www.sou-yun.cn/PoemIndex.aspx?dynasty=Tang&author=14976&type=Jie'
url='https://www.sou-yun.cn/Query.aspx?type=poem1&id=36647'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
response = requests.get(url=url,headers=headers)
html_content= response.text
#print(response.text)
# 正则表达式匹配
poem_sentences = re.findall(r"<div class='poemSentence'[^>]*>(.*?)<\/div>", html_content, re.DOTALL)

# 清理并输出提取的诗句
for sentence in poem_sentences:
    # 移除HTML标签
    clean_sentence = re.sub(r"<.*?>", "", sentence).strip()
    if clean_sentence:  # 过滤掉空句
        print(clean_sentence)

三、其他信息

提取all需要信息，title+author+sentences

python 复制代码 
import os
import re
import requests
import parsel

#url ='https://www.sou-yun.cn/PoemIndex.aspx?dynasty=Tang&author=14976&type=Jie'
url='https://www.sou-yun.cn/Query.aspx?type=poem1&id=36647'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
response = requests.get(url=url,headers=headers)
html_content= response.text
#print(response.text)
# 提取标题
title_match = re.search(r"<span class='bold'><span class='wordLink'[^>]*>(.*?)<\/span><\/span>\s*<span[^>]*>(.*?)<\/span>\s*<span class='poemAuthor'[^>]*>(.*?)<\/span>", html_content)
if title_match:
    title = title_match.group(1) + title_match.group(2)  # 合并标题部分
    author = re.sub(r"<.*?>", "", title_match.group(3)).strip()  # 处理作者

# 正则表达式匹配诗句
poem_sentences = re.findall(r"<div class='poemSentence'[^>]*>(.*?)<\/div>", html_content, re.DOTALL)

# 清理并输出提取的信息
print("标题:", title)
print("作者:", author)
print("诗句:")

for sentence in poem_sentences:
    # 移除HTML标签
    clean_sentence = re.sub(r"<.*?>", "", sentence).strip()
    if clean_sentence:  # 过滤掉空句
        print(clean_sentence)

微调格式

python 复制代码 
import os
import re
import requests
import parsel

#url ='https://www.sou-yun.cn/PoemIndex.aspx?dynasty=Tang&author=14976&type=Jie'
url='https://www.sou-yun.cn/Query.aspx?type=poem1&id=36647'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
response = requests.get(url=url,headers=headers)
html_content= response.text
#print(response.text)
# 提取标题
title_match = re.search(r"<span class='bold'><span class='wordLink'[^>]*>(.*?)<\/span><\/span>\s*<span[^>]*>(.*?)<\/span>\s*<span class='poemAuthor'[^>]*>(.*?)<\/span>", html_content)
if title_match:
    title = title_match.group(1) + title_match.group(2)  # 合并标题部分
    author = re.sub(r"<.*?>", "", title_match.group(3)).strip()  # 处理作者

# 正则表达式匹配诗句
poem_sentences = re.findall(r"<div class='poemSentence'[^>]*>(.*?)<\/div>", html_content, re.DOTALL)

# 清理并输出提取的信息
print("《 " + title + "》 （"+ author + "）")
#print("作者:", author)
#print("诗句:")

for sentence in poem_sentences:
    # 移除HTML标签
    clean_sentence = re.sub(r"<.*?>", "", sentence).strip()
    if clean_sentence:  # 过滤掉空句
        print(clean_sentence)

四、保存文档

保存到txt里面,单首诗歌

python 复制代码 
import os
import re
import requests
import parsel


#url ='https://www.sou-yun.cn/PoemIndex.aspx?dynasty=Tang&author=14976&type=Jie'
url='https://www.sou-yun.cn/Query.aspx?type=poem1&id=36647'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
response = requests.get(url=url,headers=headers)
html_content= response.text
#print(response.text)
# 提取标题
title_match = re.search(r"<span class='bold'><span class='wordLink'[^>]*>(.*?)<\/span><\/span>\s*<span[^>]*>(.*?)<\/span>\s*<span class='poemAuthor'[^>]*>(.*?)<\/span>", html_content)
if title_match:
    title = title_match.group(1) + title_match.group(2)  # 合并标题部分
    author = re.sub(r"<.*?>", "", title_match.group(3)).strip()  # 处理作者

# 正则表达式匹配诗句
poem_sentences = re.findall(r"<div class='poemSentence'[^>]*>(.*?)<\/div>", html_content, re.DOTALL)

# 清理并准备写入文件的内容
output = f"《 " + title + "》 （"+ author + "）\n"
print("《 " + title + "》 （"+ author + "）")

for sentence in poem_sentences:
    # 移除HTML标签
    clean_sentence = re.sub(r"<.*?>", "", sentence).strip()
    if clean_sentence:  # 过滤掉空句
        output += clean_sentence + "\n"
        print(clean_sentence)

# 将结果写入文本文件

with open('poem.txt', 'w', encoding='utf-8') as file:
    file.write(output)

print("信息已保存到 poem.txt")

五、多首继续

不一定是符合要求的，因为这个id暂时得不到(内容结构问题)

python 复制代码 
import os
import re
import requests
import parsel


#url ='https://www.sou-yun.cn/PoemIndex.aspx?dynasty=Tang&author=14976&type=Jie'
#url='https://www.sou-yun.cn/Query.aspx?type=poem1&id=36647'
#headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
#response = requests.get(url=url,headers=headers)
#html_content= response.text
#print(response.text)

# 指定保存文件的路径
output_file_path = 'all_poems.txt'

# 先清空（如果存在）或创建目标文件
with open(output_file_path, 'w', encoding='utf-8') as file:
    file.write("")  # 清空文件内容

# 循环下载每首诗
for poem_id in range(36647, 36848):
    url = f'https://www.sou-yun.cn/Query.aspx?type=poem1&id={poem_id}'
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.139 Safari/537.36'}
    response = requests.get(url=url, headers=headers)
    #html_content = response.text
    # 获取网页内容
    #response = requests.get(url)

    if response.status_code == 200:
        html_content = response.text

        # 提取标题
        title_match = re.search(
            r"<span class='bold'><span class='wordLink'[^>]*>(.*?)<\/span><\/span>\s*<span[^>]*>(.*?)<\/span>\s*<span class='poemAuthor'[^>]*>(.*?)<\/span>",
            html_content)
        if title_match:
            title = title_match.group(1) + title_match.group(2)  # 合并标题部分
            author = re.sub(r"<.*?>", "", title_match.group(3)).strip()  # 处理作者

            # 正则表达式匹配诗句
            poem_sentences = re.findall(r"<div class='poemSentence'[^>]*>(.*?)<\/div>", html_content, re.DOTALL)

            # 清理并准备写入文件的内容
            output = f"《 " + title + "》 （"+ author + "）\n"

            for sentence in poem_sentences:
                # 移除HTML标签
                clean_sentence = re.sub(r"<.*?>", "", sentence).strip()
                if clean_sentence:  # 过滤掉空句
                    output += clean_sentence + "\n"

            # 为每首诗添加分隔线
            output += "\n" + "=" * 50 + "\n\n"  # 分隔线，用于区分不同的诗

            # 将结果追加到文本文件
            with open(output_file_path, 'a', encoding='utf-8') as file:  # 以追加模式打开文件
                file.write(output)

            print(f"信息已保存到 {output_file_path}")
        else:
            print(f"在ID {poem_id} 的页面中找不到诗的标题或作者。")
    else:
        print(f"无法获取ID {poem_id} 的页面，状态码: {response.status_code}")

运行结果：

相关推荐
Hello.Reader7 分钟前
全面解析 Golang Gin 框架
开发语言·golang·gin
禁默18 分钟前
深入浅出：AWT的基本组件及其应用
java·开发语言·界面编程
Cachel wood25 分钟前
python round四舍五入和decimal库精确四舍五入
java·linux·前端·数据库·vue.js·python·前端框架
Code哈哈笑27 分钟前
【Java 学习】深度剖析Java多态：从向上转型到向下转型，解锁动态绑定的奥秘，让代码更优雅灵活
java·开发语言·学习
終不似少年遊*30 分钟前
pyecharts
python·信息可视化·数据分析·学习笔记·pyecharts·使用技巧
程序猿进阶31 分钟前
深入解析 Spring WebFlux：原理与应用
java·开发语言·后端·spring·面试·架构·springboot
Python之栈32 分钟前
【无标题】
数据库·python·mysql
qq_4336184433 分钟前
shell 编程(二)
开发语言·bash·shell
charlie1145141911 小时前
C++ STL CookBook
开发语言·c++·stl·c++20
袁袁袁袁满1 小时前
100天精通Python（爬虫篇）——第113天：‌爬虫基础模块之urllib详细教程大全
开发语言·爬虫·python·网络爬虫·爬虫实战·urllib·urllib模块教程
热门推荐
01〔AI 绘画〕Stable Diffusion 之 解决绘制多人或面部很小的人物时面部崩坏问题 篇02ARM学习（31）编译器对overlay方式的支持03玄机平台应急响应—webshell查杀04DisplayPort AltMode On Type-c协议_Ver2.0(学习笔记)05校验 GPT-4 真实性的三个经典问题：快速区分 GPT-3.5 与 GPT-4，并提供免费测试网站06Docker 夺命连环 15 问076个主流的工业3D管道设计软件08基于大语言模型（LLM）的合成数据生成、策展和评估的综述09(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明10红米手机使用google play