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
qz_Serene6 分钟前
C++：类和对象（上）
开发语言·c++
COOLMO研究AI10 分钟前
Python 如何在 AI 接口中实现请求幂等性：防止重复提交与重复扣费
人工智能·python·php
CTA量化套保22 分钟前
新手学量化，先做能复查的小流程
人工智能·python
西安景驰电子34 分钟前
《PTP精确时间协议系列》第一篇：从原理到应用，全面解读IEEE 1588
linux·运维·服务器·开发语言·网络·windows·php
ctlover1 小时前
Python文件操作
开发语言·python
luj_17681 小时前
塔防牌：策略与卡牌的智慧碰撞
服务器·c语言·开发语言·经验分享·算法
AndrewHZ1 小时前
图像处理入门（第005期）：颜色空间入门——RGB/HSV/CMYK/Lab
图像处理·python·opencv·hsv·rgb·色彩空间
风流 少年1 小时前
Spring AI 2.0：Tool
java·python·spring
wuyk5551 小时前
3.链表：用指针串联的动态数据结构
c语言·开发语言·数据结构·链表
郝学胜-神的一滴1 小时前
干货版《算法导论》17：二叉树核心原理、遍历逻辑与高阶实操全解
数据结构·c++·python·算法·计算机·编程
热门推荐
01GitHub 镜像站点02国内可直接用、免费额度/永久免费的大模型API清单（含 SiliconFlow、火山、阿里、智谱、百度、Kimi、DeepSeek、DMXAPI 等）03微信历史版本含下载地址（ Windows PC | 安卓 | MAC ）及设置微信不更新04VSCode+CodeX扩展，无法启动052026 国产 AI 大模型横评：DeepSeek、通义千问、Kimi、文心一言、星火、豆包谁更能打？06Agnes AI 免费 API 接入指南：文本、生图、生视频，一套接口全免费07历年考研数学一、数学二、数学三真题试卷及答案PDF08AI 编程 IDE 全景解析 2026：Agent 全面接管开发链路092026年7月AI圈大地震：GPT-5.6被政府限制、Claude入驻Slack、Anthropic自研芯片10如何新建文件夹？ 电脑新建文件夹的4种方法