# 通过城市名称构造第一类访问 url

# 访问第一类 url

# 解析该城市的公交分类，获取到想要的分类类型，构造第二类访问 url

# 访问第二类 url

# 解析分类类型的每一个公交线路，构造第三类访问 url

# 访问第三类 url

# 解析该公交路线的上、下两部分数据

# 循环第二类 -> 第三类的过程，直到爬完所有数据


import csv
from bs4 import BeautifulSoup
import requests


url = 'https://nanchang.8684.cn/'
response = requests.get(url=url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.1.4031 SLBChan/30'}, timeout=10)

"""获取数据并解析"""
soup = BeautifulSoup(response.text, 'lxml')
soup_buslayer = soup.find('div', class_='bus-layer depth w120')

# 解析分类数据
dic_result = {}
soup_buslist = soup_buslayer.find_all('div', class_='pl10')
for soup_bus in soup_buslist:
    name = soup_bus.find('span', class_='kt').get_text()
    if '以数字开头' in name:
        soup_a_list = soup_bus.find('div', class_='list')
        for soup_a in soup_a_list.find_all('a'):
            text = soup_a.get_text()
            href = soup_a.get('href')
            dic_result[text] = "https://nanchang.8684.cn" + href

print(dic_result)

bus_arr = []
index = 0

for key,value in dic_result.items():
    print ('key: ',key,'value: ',value)
    response = requests.get(url=value, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.1.4031 SLBChan/30'}, timeout=10)
    
    """获取数据并解析"""
    soup = BeautifulSoup(response.content, 'lxml')
    # 详细线路
    soup_buslist = soup.find('div', class_='list clearfix')
    for soup_a in soup_buslist.find_all('a'):
        text = soup_a.get_text()
        href = soup_a.get('href')
        title = soup_a.get('title')

        bus_arr.append([title, text, "https://nanchang.8684.cn" + href])
        
print(bus_arr)

bus_des = []
index = 0

for value in bus_arr:
    bus_name = value[0]
    # print ('路线名称: ',value[0],'value: ',value[2])
    response = requests.get(url=value[2], headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 SLBrowser/8.0.1.4031 SLBChan/30'}, timeout=10)
    
    """获取数据并解析"""
    soup = BeautifulSoup(response.text, 'lxml')
    # 详细线路
    soup_buslist = soup.find('div', class_='info')
    for soup_ul in soup_buslist.find_all('ul'):
        date = soup_ul.select('li')[0].get_text()
        money = soup_ul.select('li')[1].get_text()
        company = soup_ul.select('li')[2].select('a')[0].get_text()
        bus_des.append({"线路名称" : bus_name, "运行时间" : date,"票价" : money,"公司" : company})

print(bus_des)

#创建csv
fo = open("news.csv", "w", newline='', encoding='utf-8')
#表头
header = ["线路名称", "运行时间","票价","公司"]
writer = csv.DictWriter(fo,header)
#写入表头
writer.writeheader()
#将上一步的字典写入csv文件中
writer.writerows(bus_des)
fo.close()