58同城 房产字体 反爬

58同城 房产字体 反爬

1. 获取HTML

   url = "https://sz.58.com/zufang/"
   
   UA = {
   	"referer": "https://www.google.com/",
   	"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36"
   }
   
   html = requests.get(url=url, headers=UA)
   html.encoding="utf-8"
   
   ret = html.text
   with open('58-fangchan.txt', "w", encoding="utf-8") as f:
   	f.write(ret)
   

2. 获取字体文件

   # 1. 获取字体文件，
   with open("58-fangchan.txt", "r", encoding='utf-8') as f:
   	content = f.read()
   
   font_face = re.search(r"base64,(.*?)'\)", content).group(1)
   

3. 转换 xml， 分析关系

   from fontTools.ttLib import TTFont
   
   font = TTFont("./b-58fangchan字体.ttf")
   font.saveXML("b-58fangchan字体.xml")
   
   
   

4. 字体的映射关系

   通过，我们反复分析，得出数字取出 减1 
   

5. 全部代码

   import base64
   import io
   import re
   from lxml import etree
   
   from fontTools.ttLib import TTFont
   
   import requests
   
   # ret = base64.b64decode(font_face)
   # with open('58fangchan.ttf', 'wb') as f:
   # 	f.write(ret)
   
   # font = TTFont(ret)
   # font.saveXML('b-58.xml')
   
   
   
   url = "https://sz.58.com/zufang/"
   
   UA = {
   	"referer": "https://www.google.com/",
   	"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36"
   }
   
   # html = requests.get(url=url, headers=UA)
   # html.encoding="utf-8"
   #
   # ret = html.text
   # with open('58-fangchan.txt', "w", encoding="utf-8") as f:
   # 	f.write(ret)
   
   
   # 1. 获取字体文件，
   with open("58-fangchan.txt", "r", encoding='utf-8') as f:
   	content = f.read()
   
   font_face = re.search(r"base64,(.*?)'\)", content).group(1)
   # print(font_face)
   
   # 2. base64 解码
   ret = base64.b64decode(font_face)
   
   font = TTFont(io.BytesIO(ret))
   
   bestcmap = font['cmap'].getBestCmap()
   
   for k, v in bestcmap.items():
   	# print(k)
   	# print(v)
   	# k 此时 是10 进制 ，转成 16进制
   	k = hex(k)
   	k = k.replace('0x', '&#x') + ";"
   	# 通过，分析得出，取出v， -1 就对应数字
   	v = int(re.search(r'(\d+)', v).group(0)) -1
   	print(k)
   	print(v)
   	if k in content:
   		content = content.replace(k, str(v))
   #
   # print(content)
   # # 3 .获取 标题 ，
   resp = etree.HTML(content)
   
   lis = resp.xpath("//ul[@class='listUl']/li")
   for li in lis:
       title = li.xpath('./div[@class="des"]/h2/a/text()')
       if title:
           title = title[0]
           print(title)