python爬虫,我该怎么获取想要的内容（映射练习）

Question

练习要求：怎么通过映射的方式来获取其中的服务评分以及电话号码，并能够进行完整的结果打印
提问：svg坐标与css坐标是相反数，为什么寻找svg坐标还要进行计算）
问题:
1.无法打印出需要的资料

import re
import requests
from parsel import Selector

url = 'http://www.porters.vip/confusion/food.html'
svg_url = 'http://www.porters.vip/confusion/font/food.svg'
css_url = 'http://www.porters.vip/confusion/css/food.css'

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
    'Host': 'www.porters.vip'
}

res = requests.get(url,headers=headers)
svg_text = requests.get(svg_url).text
css_text = requests.get(css_url).text

# 下载文本
# with open('柳州.text','w',encoding='utf-8') as f:
#     f.write(res.content.decode())
# with open('柳州_svg.svg','w',encoding='utf-8') as f:
#     f.write(svg_res.content.decode())
# with open('柳州_css.css','w',encoding='utf-8') as f:
#     f.write(css_res.content.decode())
# 查找所对应的css数据
css_class_name = 'vhkqsc'
pile = '.%s(background: -(\d+)px -(\d+)px;)%css_class_name
pattern = re.compile(pile)      # 先编译
css = css_text.replace('\n','').replace(' ','')
print(css)
coord = pattern.findall(css)
print(coord)  #???

if coord:
    x,y = coord[0]
    x,y = int(x),int(y)
    print(x,y)      #???

# 因为svg有四个text，需要寻找对应css标签
svg_data = Selector(svg_text)

texts = svg_data.xpath("//text")
print(texts)

# 根据y值来确定，css的位置 --》 svg对应的值，取最近的一个值
axiy = [i.attrib.get('y') for i in texts if y<=int(i.attrib.get('y'))][0]
print(axiy)

# 提取对应的y的text
svg_text_ = svg_data.xpath("//span[@y=%s]/text()"%axiy).extract_first
print(svg_text_)        #???

# 提取字体大小
fout_size = re.search('font-size:(\d+)px;',svg_text).group(1)
print(fout_size)        #???

# css对应的坐标/字体大小=svg坐标
position = x//int(fout_size)

number = svg_text_[position]
print(number)       #???

print(x,y) 返回为[]

1.确定url
确定svg与css的url

2.发送请求

3.进行css分析每个映射数字的坐标

4.由css对照svg中的text进行查找，并带入字符大小进行计算svg的坐标

5.使用正则，将svg中对应的值添加进，获取完整的信息，并保存

Answer 1

因为题主将css中的空格全部替换掉了，但是正则中还有空格，并且正则分组用()，不是{}，而且svg中没有span标签，是text
改下面就可以了

import re
import requests
from parsel import Selector
from lxml import etree
def getCssNumber(css_class_name):
    n=kvCls2Number.get(css_class_name,-1)
    if n!=-1:
        return n

    pile = '.%s{background:-(\d+)px-(\d+)px;}'%css_class_name
    pattern = re.compile(pile)      # 先编译
    coord = pattern.findall(css)
    x,y = coord[0]
    x,y = int(x),int(y)

    # 根据y值来确定，css的位置 --》 svg对应的值，取最近的一个值
    axiy = [i.attrib.get('y') for i in texts if y<=int(i.attrib.get('y'))][0]

    # 提取对应的y的text
    svg_text_ = svg_data.xpath("//text[@y=%s]/text()"%axiy).extract_first()

    # 提取字体大小
    fout_size = re.search('font-size:(\d+)px;',svg_text).group(1)

    # css对应的坐标/字体大小=svg坐标
    position = x//int(fout_size)
    number = svg_text_[position]

    kvCls2Number[css_class_name]=number
    return number



url = 'http://www.porters.vip/confusion/food.html'
svg_url = 'http://www.porters.vip/confusion/font/food.svg'
css_url = 'http://www.porters.vip/confusion/css/food.css'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
    'Host': 'www.porters.vip'
}
svg_text = requests.get(svg_url).text
css_text = requests.get(css_url).text

css = css_text.replace('\n','').replace(' ','')
svg_data = Selector(svg_text)
texts = svg_data.xpath("//text")

kvCls2Number={}#用来存储已经获取到的样式对应的数字，不需要每次重复获取


res = requests.get(url,headers=headers)

tree=etree.HTML(res.text)
detail=tree.xpath('//div[@class="col details"]')[0]
span=detail.xpath('.//span[@class="comment_score"]/span')[-1]
serviceNumber=(getCssNumber(span.xpath('.//d/@class')[0]))
serviceNumber+=span.xpath('text()')[-1]
print('服务：'+serviceNumber)

phoneCls=detail.xpath('.//div[@class="col more"]/d/@class')
phone=""
for c in phoneCls:
    if c=="":
        phone+="-"
    else:
        phone+=getCssNumber(c)


print('电话：'+phone)

 

有帮助或启发麻烦点下【采纳该答案】，谢谢~~有其他问题可以继续交流~