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：

复制代码 
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
AiXed6 小时前
PC微信协议之AES-192-GCM算法
前端·数据库·python
灵光通码7 小时前
神经网络基本概念
python·神经网络
武子康8 小时前
Java-171 Neo4j 备份与恢复 + 预热与执行计划实战
java·开发语言·数据库·性能优化·系统架构·nosql·neo4j
Petrichor_H_9 小时前
DAY 31 文件的规范拆分和写法
python
怪兽20149 小时前
fastjson在kotlin不使用kotlin-reflect库怎么使用?
android·开发语言·kotlin
ClearLiang9 小时前
Kotlin-协程的挂起与恢复
开发语言·kotlin
q***31839 小时前
爬虫基础之爬取某基金网站+数据分析
爬虫·数据挖掘·数据分析
彭同学学习日志9 小时前
Kotlin Fragment 按钮跳转报错解决：Unresolved reference ‘floatingActionButton‘
android·开发语言·kotlin
海域云赵从友9 小时前
破解跨境数据传输瓶颈：中国德国高速跨境组网专线与本地化 IP 的协同策略
开发语言·php
咚咚王者10 小时前
人工智能之编程进阶 Python高级：第九章 爬虫类模块
开发语言·python
热门推荐
01GitHub 镜像站点02BongoCat - 跨平台键盘猫动画工具03UV安装并设置国内源04安娜的档案(Anna’s Archive) 镜像网站/国内最新可访问入口（持续更新）05Linux下V2Ray安装配置指南06《大数据技术原理与应用》实验报告三 熟悉HBase常用操作07jdk21下载、安装（Windows、Linux、macOS）082025 最新教程：注册并切换到美区 Apple ID09综合整理：pdf预览显示：你尝试预览的文件可能对你的计算机有害。如果你信任此文件以及其来源，请打开此文件以看其内容，如何解决以正常预览文件10智能库存管理的需求预测模型：从业务痛点到落地代码的完整实践