python-css偏移反爬（一）

目标网站：http://www.porters.vip/confusion/flight.html#

css法详解可到崔佬的https://cuiqingcai.com/8678.html查看，在此以表感谢，学习了。

import requests
import re
from parsel import Selector

# css法
def spider():
    url = 'http://www.porters.vip/confusion/flight.html'
    resp = requests.get(url)
    sel = Selector(resp.text)
    em = sel.css('em.rel')
    for element in em:
        # 定位所有的<b>标签
        element_b = element.css('b').extract()
        b1 = Selector(element_b.pop(0))
        b1_style = b1.css('b::attr("style")').get()
        # print(b1_style) # width:48px;left:-48px   width:64px;left:-64px
        b1_width = ''.join(re.findall('width:(.*)px;', b1_style))
        number = int(int(b1_width) / 16)  # 3  4
        # 获取第 1 对 <b> 标签中的值(列表)
        base_price = b1.css('i::text').extract()[:number]
        # print(base_price)
        alternate_price = []
        for eb in element_b:
            eb = Selector(eb)
            # 提取<b>标签的 style 属性值
            style = eb.css('b::attr("style")').get()
            # 获得具体的位置
            position = ''.join(re.findall('left:(.*)px', style))
            # 获得该标签下的数字
            value = eb.css('b::text').get()
            # 将<b>标签的位置信息和数字以字典的格式添加到替补票价列表中
            alternate_price.append({'position': position, 'value': value})
        # print(alternate_price)
        for al in alternate_price:
            position = int(al.get('position'))
            value = al.get('value')
            # 计算下标，以 16px 为基准
            index = int(position / 16)
            # 替换第一对<b>标签值列表中的元素，也就是完成值覆盖操作
            base_price[index] = value
        print(base_price)

# spider()

# xpath法一：
def spider1():
    url = 'http://www.porters.vip/confusion/flight.html'
    resp = requests.get(url)
    sel = Selector(resp.text)
    em = sel.xpath('//em[@class="rel"]')
    for element in em:
        element_b = element.xpath('./b').extract()
        b1 = Selector(element_b.pop(0))
        b1_style = b1.xpath('//@style').extract_first()
        b1_width = re.search('width:(.*)px;', b1_style).group(1)
        number = int(int(b1_width) / 16)  # 3  4
        base_price = b1.xpath('//i/text()').extract()[:number]
        # print(base_price)
        alternate_price = []
        for eb in element_b:
            eb = Selector(eb)
            style = eb.xpath('//@style').extract_first()
            position = re.search('left:(.*)px', style).group(1)
            value = eb.xpath('//text()').extract_first()
            alternate_price.append({'position': position, 'value': value})
        # print(alternate_price)
        for al in alternate_price:
            position = int(al.get('position'))
            value = al.get('value')
            index = int(position / 16)
            base_price[index] = value
        print(base_price)


# spider1()

# xpath法二：
def spider2():
    url = 'http://www.porters.vip/confusion/flight.html'
    resp = requests.get(url)
    sel = Selector(resp.text)
    em = sel.xpath('//em[@class="rel"]')
    for element in em:
        b1_style = element.xpath('./b[1]/@style').extract_first()
        b1_width = re.search('width:(.*)px;', b1_style).group(1)
        number = int(int(b1_width) / 16)  # 3  4
        base_price = element.xpath('./b[1]/i/text()').extract()[:number]
        # 取当前节点下所有兄弟标签
        element_b = element.xpath('./b[1]/following-sibling::*').extract()
        # 效果等同于上一行
        # element_b = element.xpath('./b[position()>1]').extract()
        alternate_price = []
        for eb in element_b:
            eb = Selector(eb)
            style = eb.xpath('//@style').extract_first()
            position = re.search('left:(.*)px', style).group(1)
            value = eb.xpath('//text()').extract_first()
            alternate_price.append({'position': position, 'value': value})
        # print(alternate_price)
        for al in alternate_price:
            position = int(al.get('position'))
            value = al.get('value')
            index = int(position / 16)
            base_price[index] = value
        print(base_price)


spider2()