技術標籤：pythonpythonxpathhtml資料分析

目標網站：https://www.aqistudy.cn/historydata/

# 開發時間：2020/12/27 22:00
# 開發工具：PyCharm
# 開發者：Friday
# 網址 https://www.aqistudy.cn/historydata/
import requests
from lxml import etree

if __name__ == "__main__":
    headers = {
        'Referer': 'http://pic.netbian.com/4kmeinv/index_2.html'
 
,
        'user_agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    url = 'https://www.aqistudy.cn/historydata/'
    response = requests.get(url = url, headers = headers)
    page_text = response.text
    tree = etree.HTML(page_text)
 

    #方法一：
    # # 熱門城市
    # host_city_list = tree.xpath('//div[@class="bottom"]/ul/li')
    # host_name_list = []
    # for li in  host_city_list:
    #     host_name = li.xpath('./a/text()')[0]
    #     host_name_list.append(host_name)
    # # print(host_name_list)
    #
    # #1.
    # # all_city_list = []
 

    # # all_city_ul_list = tree.xpath('//div[@class="bottom"]/ul')
    # # for ul in all_city_ul_list:
    # #     get_li_list = ul.xpath('./div/li')
    # #     for li in get_li_list:
    # #         name = li.xpath('./a/text()')[0]
    # #         host_name_list.append(name)
    # #2.
    # # all_city_li = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
    # # for li in all_city_li:
    # #     name = li.xpath('./a/text()')[0]
    # #     host_name_list.append(name)
    # print(host_name_list)
    # print(len(host_name_list))

    #方法二：
    a_list = tree.xpath('//div[@class="bottom"]/ul/li/a | //div[@class="bottom"]/ul/div[2]/li/a')
    all_city_names = []
    for a in a_list:
        city_name = a.xpath('./text()')[0]
        all_city_names.append(city_name)
    print(all_city_names)
    print(len(all_city_names))

總結：檢視網頁的程式碼結構，比較容易想到的就是進行兩次xpath解析，分別獲取“熱門城市”和“全部城市”的li標籤，但仔細思考，還是可以進一步優化的，由於我們要爬取的城市名稱都在a標籤下，所以我們可以利用xpath同時解析出兩者所對應的a標籤，然後再統一操作。