书籍推荐
如果你对Python网络爬虫感兴趣，强烈推荐你阅读《Python网络爬虫入门到实战》。这本书详细介绍了Python网络爬虫的基础知识和高级技巧，是每位爬虫开发者的必读之作。详细介绍见👉： 《Python网络爬虫入门到实战》 书籍介绍
正则抓取腾讯动漫数据
import requests
import re
import threading
from queue import Queue
def format_html(html):
li_pattern = re.compile('<li class="ret-search-item clearfix">[\s\S]+?</li>')
title_pattern = re.compile('title="(.*?)"')
img_src_pattern = re.compile('data-original="(.*?)"')
update_pattern = re.compile('<span class="mod-cover-list-text">(.*?)</span>')
tags_pattern = re.compile('<span href="/Comic/all/theme/.*?" target="_blank">(.*?)</span>')
popularity_pattern = re.compile('<span>人气：<em>(.*?)</em></span>')
items = li_pattern.findall(html)
for item in items:
title = title_pattern.search(item).group(1)
img_src = img_src_pattern.search(item).group(1)
update_info = update_pattern.search(item).group(1)
tags = tags_pattern.findall(item)
popularity = popularity_pattern.search(item).group(1)
data_queue.put(f'{title},{img_src},{update_info},{"#".join(tags)},{popularity}\n')
def run(index):
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
response = requests.get(f"https://ac.qq.com/Comic/index/page/{index}", headers=headers)
html = response.text
format_html(html)
except Exception as e:
print(f"Error occurred while processing page {index}: {e}")
finally:
semaphore.release()
if __name__ == "__main__":
data_queue = Queue()
semaphore = threading.BoundedSemaphore(5)
lst_record_threads = []
for index in range(1, 3):
print(f"正在抓取{index}")
semaphore.acquire()
t = threading.Thread(target=run, args=(index,))
t.start()
lst_record_threads.append(t)
for rt in lst_record_threads:
rt.join()
with open("./qq_comic_data.csv", "a+", encoding="gbk") as f:
while not data_queue.empty():
f.write(data_queue.get())
print("数据爬取完毕")
Flask展示数据
上面能够实现爬取数据，但是我希望展示在前端。
main.py代码如下：
# coding= gbk
from flask import Flask, render_template
import csv
app = Flask(__name__)
def read_data_from_csv():
with open("qq_comic_data.csv", "r", encoding="utf-8") as f:
reader = csv.reader(f)
data = list(reader)[1:] # 跳过标题行
# 统一转换人气数据为浮点数（单位：亿）
for row in data:
popularity = row[4]
if '亿' in popularity:
row[4] = float(popularity.replace('亿', ''))
elif '万' in popularity:
row[4] = float(popularity.replace('万', '')) / 10000 # 将万转换为亿
# 按人气排序并保留前10条记录
data.sort(key=lambda x: x[4], reverse=True)
return data[:10]
@app.route('/')
def index():
comics = read_data_from_csv()
return render_template('index.html', comics=comics)
if __name__ == '__main__':
app.run(debug=True)
templates/index.html如下：
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>漫画信息</title>
<style>
body {
font-family: Arial, sans-serif;
background-color: #f4f4f4;
color: #333;
line-height: 1.6;
padding: 20px;
}
.container {
width: 80%;
margin: auto;
overflow: hidden;
}
h1 {
text-align: center;
color: #333;
}
.comic {
background: #fff;
margin-bottom: 20px;
padding: 15px;
border-radius: 10px;
box-shadow: 0 5px 10px rgba(0,0,0,0.1);
}
.comic h2 {
margin-top: 0;
}
.comic p {
line-height: 1.25;
}
.comic:nth-child(even) {
background: #f9f9f9;
}
</style>
</head>
<body>
<div class="container">
<h1>人气前10的漫画</h1>
{% for comic in comics %}
<div class="comic">
<h2>{{ comic[0] }}</h2>
<p><strong>更新信息：</strong>{{ comic[2] }}</p>
<p><strong>类型：</strong>{{ comic[3] }}</p>
<p><strong>人气：</strong>{{ comic[4] }}</p>
</div>
{% endfor %}
</div>
</body>
</html>
效果如下：