Python爬虫---汽车之家字体反爬

# 那么便开始通过字体库进行解析
world = TTFont('./world.ttf')
# 读取响应的映射关系
uni_list = world['cmap'].tables[0].ttFont.getGlyphOrder() # 'cmap' 表示汉字对应的映射 为unicode编码
print(uni_list) # 按顺序拿到各个字符的unicode编码
# 打印结果：
['.notdef', 'uniEDE8', 'uniED35', 'uniED87', 'uniECD3', 'uniED25', 'uniEC72', 'uniEDB2', 'uniEE04', 'uniED51', 'uniEC9D', 'uniECEF', 'uniEC3C', 'uniEC8D', 'uniEDCE', 'uniED1B', 'uniED6C', 'uniECB9', 'uniEDFA', 'uniEC57', 'uniED98', 'uniEDEA', 'uniED36', 'uniEC83', 'uniECD5', 'uniEC21', 'uniED62', 'uniEDB4', 'uniED00', 'uniED52', 'uniEC9F', 'uniEDDF', 'uniEC3D', 'uniED7E', 'uniECCA', 'uniED1C', 'uniEC69', 'uniECBB', 'uniEDFB']
# .notdef 并不是汉字的映射， 而是表示字体家族名称。
将映射列表转换成unicode的类型，因为自己文中获取的是字符串unicode类型的，当然你也可以转化为utf-8,不过你获取的文章内容也要转化为utf-8
unicode_list= [eval(r"u'u" + uni[3:] + "'") for uni in uni_list[1:]]

# coding:utf-8
import re
import requests
from scrapy import Selector
from fontTools.ttLib import TTFont
class QiCheZhiJiaSpider:
 def article_content(self):
 url = 'https://club.autohome.com.cn/bbs/thread/2d8a42404ba24266/77486027-1.html#pvareaid=2199101'
 headers = {
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36'
 }
 try:
 response = requests.get(url=url, headers=headers).text
 response_info = Selector(text=response)
 except BaseException as e:
 print(e)
 else:
 content = response_info.xpath('//div[@class="tz-paragraph"]//text()').extract() # 获取列表的形式内容。
 # print(content)
 content_str = ''.join(content)
 # 紧接着获取字体的链接
 world_href = re.findall(r",url('(//.*.ttf)').*", response, re.M or re.S)[0]
 world_href = 'https:' + world_href
 world_content = requests.get(url=world_href, headers=headers).content
 # 对获取到的字体进行下载..........
 with open('./world.ttf', 'wb') as f:
 f.write(world_content)
 # 那么便开始通过字体库进行解析
 world = TTFont('./world.ttf')
 # 读取响应的映射关系
 uni_list = world['cmap'].tables[0].ttFont.getGlyphOrder()
 unicode_list = [eval(r"u'u" + uni[3:] + "'") for uni in uni_list[1:]]
 world_list = ["右", "远", "高", "呢", "了", "短", "得", "矮", "多", "二", "大", "一", "不", "近",
 "是", "着", "五", "三", "九", "六", "少", "好", "上", "七", "和", "很", "十",
 "四", "左", "下", "八", "小", "坏", "低", "长", "更", "的", "地"] # # 录入字体文件中的字符。必须要以国际标准的unicode编码
 for i in range(len(unicode_list )):
 content_str = content_str.replace(unicode_list [i], world_list[i])
 print(content_str)
if __name__ == '__main__':
 qi_che_zhi_jia = QiCheZhiJiaSpider()
 qi_che_zhi_jia.article_content()