import requests
from lxml import etree
from fake_useragent import UserAgent
import time
import re
import random

# USER_AGENTS
USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser;",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
]

# 保存文件
def save(long_str):
    try:
        with open(f"exhibition.csv", "a+", encoding="utf-8") as f:
            f.write(long_str)
    except Exception as e:
        print(e)

# 获取详情页数据
def get_detail(url):
    try:
        headers = {"User-Agent": random.choice(USER_AGENTS)}
        res = requests.get(url=url, headers=headers)
        text = res.text
        # 将 html 转换成 Element 对象
        html = etree.HTML(text)
        # 详细地址
        address_detail = html.xpath("//span[@class='fl mr10']/text()")[0]
        # 时间间隔
        time_interval = html.xpath(
            "//div[@class='h25 line25 s6 f14 w100s mb10']/text()")[3].strip()

        # 票价
        ticket_price = html.xpath("//b[@class='f40']/text()")[0]
        # 匹配得分
        score_url = html.xpath("//div[@class='mt10']/img/@src")[0]
        score = re.search(
            r"//static.nyato.cn/expo-image/stars/star-(\d\.\d).png", score_url).group(1)
        # 其它信息
        other = ",".join(html.xpath(
            "//span[@class='sf6 f18 fwb ml15']/text()"))
        return ticket_price, time_interval, address_detail, score, other

    except Exception as e:
        print("详情页BUG")
        print(url)
        time.sleep(4)
        get_detail(url)
        print(e)


def run(url):

    try:
        headers = {"User-Agent": random.choice(USER_AGENTS)}
        res = requests.get(url=url, headers=headers)
        text = res.text
        # 将 html 转换成 Element 对象
        html = etree.HTML(text)
        # xpath 路径提取 @class 为选取 class 属性
        lis = html.xpath("//ul[@class='w980 pt20']/li")

        # 遍历 Elements 节点
        for li in lis:
            href = li.xpath(".//a/@href")[0]
            title = li.xpath(".//a/@title")[0]
            city = li.xpath(".//span[@class='w120 fl']/text()")[0].strip()
            ticket_price, time_interval, address_detail, score, other = get_detail(
                href)
            long_str = f"{href},{title},{city},{ticket_price},{time_interval},{address_detail},{score},{other}\n"
            save(long_str)

    except Exception as e:
        print("列表页BUG")
        print(url)
        time.sleep(4)
        run(url)
        print(e)


if __name__ == '__main__':
    urls = []
    for i in range(1, 1313):
        urls.append(f"https://www.nyato.com/manzhan/?type=expired&p={i}")
    for url in urls:
        print(f"正在抓取{url}")
        run(url)

    print("全部爬取完毕")

上述代码在提取漫展评分时，引入了 re 模块，在字符串提取内容上，正则表达式的适配性还是比较高的。

通过正则直接从图片地址中将评分提取出来，本案例可以这样操作的原因是，分数图片有规则可循，图片连接如下，即分数图片由分数连接而成。

# 3.0 分
//static.nyato.cn/expo-image/stars/star-3.0.png
# 3.5 分
//static.nyato.cn/expo-image/stars/star-3.5.png

# 匹配得分
score_url = html.xpath("//div[@class='mt10']/img/@src")[0]
score = re.search(r"//static.nyato.cn/expo-image/stars/star-(\d\.\d).png", score_url).group(1)

address_detail = html.xpath("//span[@class='fl mr10']/text()")[0]
# 时间间隔
time_interval = html.xpath("//div[@class='h25 line25 s6 f14 w100s mb10']/text()")[3].strip()
# 票价
ticket_price = html.xpath("//b[@class='f40']/text()")[0]
# 匹配得分
score_url = html.xpath("//div[@class='mt10']/img/@src")[0]