python-爬虫-三字代码网站爬取

三字代码 http://www.6qt.net/

爬取城市、三字代码、所属国家、国家代码、四字代码、机场名称、英文名称、查询次数

import requests

url = 'http://www.6qt.net/'
r = requests.get(url)
r.encoding='gb2312'
print(r.text)

使用xpath解析，得到城市名

html.fromstring(html, base_url=None, parser=None, **kw)
Parse the html, returning a single element/document.解析html，返回单个元素/文档

import requests
from lxml import html

url = 'http://www.6qt.net/'
r = requests.get(url)
r.encoding='gb2312'
data_html = html.fromstring(r.text)
# 提取所有class属性为tdbg的tr元素
tr_html = data_html.xpath('//tr[@class="tdbg"]')# 得到Element对象列表# 
for tr in tr_html:
    city_name = tr.xpath('td[1]/a/text()')
    if city_name:
        print(city_name[0])

完整代码

import requests
from lxml import html

url = 'http://www.6qt.net/'
r = requests.get(url)
r.encoding='gb2312'
data_html = html.fromstring(r.text)
tr_html = data_html.xpath('//tr[@class="tdbg"]')
for tr in tr_html:
    data = {}
    city_name = tr.xpath('td[1]/a/text()')
    if city_name:
        data['city_name'] = city_name[0].replace('\xa0','')
    tcc = tr.xpath('td[2]/a/text()')	# Three character code三字代码
    if city_name:
        data['tcc'] = tcc[0].replace('\xa0','')
    country = tr.xpath('td[3]/a/u/text()')
    if city_name:
        data['country'] = country[0]
    country_code = tr.xpath('td[4]/a/u/text()')
    if city_name:
        data['country_code'] = country_code[0]
    fcc = tr.xpath('td[5]/a/u/text()')
    if city_name:
        if fcc:		# 有的城市没有四字代码
            data['fcc'] = fcc[0]
        else:
            data['fcc'] = ''	# 没有四字代码用空字符串代替
    airport_name = tr.xpath('td[6]/text()')
    if city_name:
        data['airport_name'] = airport_name[0].replace('\xa0','')
    en_name = tr.xpath('td[7]/text()')
    if city_name:
        data['en_name'] = en_name[0].replace('\xa0','')
    number = tr.xpath('td[8]/a/text()')
    if city_name:
        data['number'] = number[0]
    
    if data:
        print(data)

ASCII 字符集中的\xa0代表的是非打印字符"非断行空格"，也称为"不间断空格"，在网页中通常用于表示空格或保持文本的格式。在 HTML 中，它被称为“ ”实体。

---

可以使用lxml的tostring()函数将一个Element对象转换成可读的代码。例如：

from lxml import etree

# 创建一个HTML文档的根元素
root = etree.Element("html")

# 创建一个标签并添加到根元素中
head = etree.SubElement(root, "head")

# 创建一个