xpath 爬取北京公交相关数据

# 公交信息的基础 URL
url = 'https://beijing.8684.cn'
url_template = url + '/list{}'

# 生成要爬取的公交 URL 列表
bus_url_list_test = [i for i in range(1, 10)]  # 修改范围以获取更多公交列表
bus_url_list = []

for num in bus_url_list_test:
    urls = url_template.format(num)
    bus_url_list.append(urls)

# 准备一个列表来存储每个公交详情的 URL
bus_load_num_list = []

# 从列表页面收集每个公交详情的 URL
for bul in bus_url_list:
    response = requests.get(bul, headers=header)  # 向每个公交列表页面发送请求
    content = response.content.decode('utf-8')
    html = etree.HTML(content)

    # 使用 XPath 提取公交详情链接
    bus_href_list = html.xpath("//div[@class='list clearfix']//a/@href")

    for bus_href in bus_href_list:
        url_str = url + bus_href
        bus_load_num_list.append(url_str)  # 将完整 URL 添加到列表中

import requests
from lxml import etree
from time import sleep

#  定义请求头，以模拟浏览器请求
header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'
}

# 公交信息的基础 URL
url = 'https://beijing.8684.cn'
url_template = url + '/list{}'

# 生成要爬取的公交 URL 列表
bus_url_list_test = [i for i in range(1, 10)]  # 修改范围以获取更多公交列表
bus_url_list = []

for num in bus_url_list_test:
    urls = url_template.format(num)
    bus_url_list.append(urls)

# 准备一个列表来存储每个公交详情的 URL
bus_load_num_list = []

# 从列表页面收集每个公交详情的 URL
for bul in bus_url_list:
    response = requests.get(bul, headers=header)  # 向每个公交列表页面发送请求
    content = response.content.decode('utf-8')
    html = etree.HTML(content)

    # 使用 XPath 提取公交详情链接
    bus_href_list = html.xpath("//div[@class='list clearfix']//a/@href")

    for bus_href in bus_href_list:
        url_str = url + bus_href
        bus_load_num_list.append(url_str)  # 将完整 URL 添加到列表中

# 遍历每个公交详情 URL 以获取信息
for bln in bus_load_num_list:
    try:
        response = requests.get(bln, headers=header)  # 请求详细的公交信息
        content = response.content.decode('utf-8')
        html = etree.HTML(content)

        # 使用 XPath 提取公交信息
        bus_name = html.xpath("//div[@class='info']//span/@aria-label")
        bus_type = html.xpath("//h1[@class='title']//a/text()")

        bus_info = html.xpath("//ul[@class='bus-desc']//li/text()")[:-1]
        bus_time = bus_info[0]
        ticket = bus_info[1:]

        gongsi = html.xpath("//ul[@class='bus-desc']//li//a/@title")
        gengxin = html.xpath("//ul[@class='bus-desc']//li//span/text()")
        licheng = html.xpath("//div[@class='change-info mb20']//text()")
        wang_info = html.xpath("//div[@class='trip']/text()")
        fan_info = html.xpath("//div[@class='trip']/text()")[1:]
        wang_fan_load_list = html.xpath("//div[@class='bus-lzlist mb15']//ol//a/text()")

        # 将加载列表分为去程和返程两部分
        wang_buff = wang_fan_load_list[:(len(wang_fan_load_list) // 2)]
        fan_buff = wang_fan_load_list[(len(wang_fan_load_list) // 2):]

        # 将所有提取的数据放入一个列表
        data_list = [
            bus_name[0] if bus_name else 'None',
            bus_type[0] if bus_type else 'None',
            bus_time if bus_time else 'None',
            ticket[0] if ticket else 'None',
            ','.join(gongsi) if gongsi else 'None',
            gengxin[1] if len(gengxin) > 1 else 'None',
            licheng[0] if licheng else 'None',
            wang_info[0] if wang_info else 'None',
            ','.join(wang_buff) if wang_buff else 'None',
            fan_info[0] if fan_info else 'None',
            ','.join(fan_buff) if fan_buff else 'None'
        ]

        # 将数据写入文件
        with open('BeiJing_Bus_Info.txt', 'a', encoding='utf-8') as file:
            file.write('@'.join(data_list) + '\n')

        # 打印提取的数据
        print(f"= = = = = = = = = = = = = = = = = {bus_name[0] if bus_name else '未知数据'} 爬取完成 = = = = = = = = = = = = = = = =")

    except Exception as e:
        # 如果发生错误，打印错误信息并将 data_list 设置为包含 'None' 的列表
        print(f"从 {bln} 获取数据时发生错误: {e}")
        data_list = ["None"] * 10  # 假设预期有 10 个字段
        print(f"= = = = = = = = = = = = = = = = = 未知数据 爬取失败 = = = = = = = = = = = = = = = =")

    sleep(1)  # 暂停 1 秒以避免对服务器造成过大压力

import csv

# 读取数据文本文件
with open('BeiJing_Bus_Info.txt', 'r', encoding='utf-8') as infile:
    data = infile.readlines()

# 处理数据并写入CSV文件
with open('BeiJing_Bus_Info.csv', 'w', encoding='utf-8', newline='') as outfile:
    csv_writer = csv.writer(outfile)

    for line in data:
        # 以@为分隔符分割每一行
        row = line.strip().split('@')
        # 写入CSV文件
        csv_writer.writerow(row)

print("数据已成功写入 BeiJing_Bus_Info.csv")

# 登录mysql
# 建库
CREATE DATABASE `studb` DEFAULT CHARACTER SET utf8mb3;

# 建表
CREATE TABLE `stu_businfo` (
   `id` int NOT NULL AUTO_INCREMENT,
   `bus_name` varchar(1000) DEFAULT 'None',
   `bus_type` varchar(1000) DEFAULT 'None',
   `bus_time` varchar(1000) DEFAULT 'None',
   `ticket` varchar(1000) DEFAULT 'None',
   `gongsi` varchar(1000) DEFAULT 'None',
   `gengxin` varchar(1000) DEFAULT 'None',
   `licheng` varchar(1000) DEFAULT 'None',
   `wang_info` varchar(1000) DEFAULT 'None',
   `wang_buff` varchar(1000) DEFAULT 'None',
   `fan_info` varchar(1000) DEFAULT 'None',
   `fan_buff` varchar(1000) DEFAULT 'None',
   PRIMARY KEY (`id`)
 ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;

# 将文件拷贝一份至相应位置
 cp BeiJing_Bus_Info.txt /var/lib/mysql-files/

# 将txt文件数据导入mysql
LOAD DATA INFILE '/var/lib/mysql-files/BeiJing_Bus_Info.txt' INTO TABLE stu_businfo FIELDS TERMINATED BY '@' LINES TERMINATED BY '\n' (bus_name,bus_type,bus_time,ticket,gongsi,gengxin,licheng,wang_info,wang_buff,fan_info,fan_buff);