<TTGlyph name="uniE183" xMin="0" yMin="-12" xMax="516" yMax="706"><contour><pt x="134" y="195" on="1"/><pt x="144" y="126" on="0"/><pt x="217" y="60" on="0"/><pt x="271" y="60" on="1"/><pt x="335" y="60" on="0"/><pt x="423" y="158" on="0"/><pt x="423" y="311" on="0"/><pt x="337" y="397" on="0"/><pt x="270" y="397" on="1"/><pt x="227" y="397" on="0"/><pt x="160" y="359" on="0"/><pt x="140" y="328" on="1"/><pt x="57" y="338" on="1"/><pt x="126" y="706" on="1"/><pt x="482" y="706" on="1"/><pt x="482" y="622" on="1"/><pt x="197" y="622" on="1"/><pt x="158" y="430" on="1"/><pt x="190" y="452" on="0"/><pt x="258" y="475" on="0"/><pt x="293" y="475" on="1"/><pt x="387" y="475" on="0"/><pt x="516" y="346" on="0"/><pt x="516" y="243" on="1"/><pt x="516" y="147" on="0"/><pt x="459" y="75" on="1"/><pt x="390" y="-12" on="0"/><pt x="271" y="-12" on="1"/><pt x="173" y="-12" on="0"/><pt x="112" y="42" on="1"/><pt x="50" y="98" on="0"/><pt x="42" y="188" on="1"/></contour><instructions/></TTGlyph>

# 解析字体库font文件
baseFont = TTFont('base.otf')
maoyanFont = TTFont('maoyan.otf')
uniList = maoyanFont['cmap'].tables[0].ttFont.getGlyphOrder()
numList = []
baseNumList = ['.', '3', '5', '1', '2', '7', '0', '6', '9', '8', '4']
baseUniCode = ['x', 'uniE64B', 'uniE183', 'uniED06', 'uniE1AC', 'uniEA2D', 'uniEBF8',
'uniE831', 'uniF654', 'uniF25B', 'uniE3EB']
for i in range(1, 12):maoyanGlyph = maoyanFont['glyf'][uniList[i]]for j in range(11):baseGlyph = baseFont['glyf'][baseUniCode[j]]if maoyanGlyph == baseGlyph:numList.append(baseNumList[j])break

# -*- coding:utf-8 -*-
import requests
from lxml import html
import re
import woff2otf
from fontTools.ttLib import TTFont#抓取maoyan票房
class MaoyanSpider:#页面初始化def __init__(self):self.headers = {"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8","Accept-Encoding": "gzip, deflate, br","Accept-Language": "zh-CN,zh;q=0.8","Cache-Control": "max-age=0","Connection": "keep-alive","Upgrade-Insecure-Requests": "1","Content-Type": "application/x-www-form-urlencoded; charset=UTF-8","User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.36"}# 获取票房def getNote(self):url = "http://maoyan.com"host = {'host':'maoyan.com','refer':'http://maoyan.com/news',}headers = dict(self.headers.items() + host.items())# 获取页面内容r = requests.get(url, headers=headers)#print r.textresponse = html.fromstring(r.text)# 匹配ttf fontcmp = re.compile(",\n           url\('(//.*.woff)'\) format\('woff'\)")rst = cmp.findall(r.text)ttf = requests.get("http:" + rst[0], stream=True)with open("maoyan.woff", "wb") as pdf:for chunk in ttf.iter_content(chunk_size=1024):if chunk:pdf.write(chunk)# 转换woff字体为otf字体woff2otf.convert('maoyan.woff', 'maoyan.otf')# 解析字体库font文件baseFont = TTFont('base.otf')maoyanFont = TTFont('maoyan.otf')uniList = maoyanFont['cmap'].tables[0].ttFont.getGlyphOrder()numList = []baseNumList = ['.', '3', '5', '1', '2', '7', '0', '6', '9', '8', '4']baseUniCode = ['x', 'uniE64B', 'uniE183', 'uniED06', 'uniE1AC', 'uniEA2D', 'uniEBF8','uniE831', 'uniF654', 'uniF25B', 'uniE3EB']for i in range(1, 12):maoyanGlyph = maoyanFont['glyf'][uniList[i]]for j in range(11):baseGlyph = baseFont['glyf'][baseUniCode[j]]if maoyanGlyph == baseGlyph:numList.append(baseNumList[j])breakuniList[1] = 'uni0078'utf8List = [eval("u'\u" + uni[3:] + "'").encode("utf-8") for uni in uniList[1:]]# 获取发帖内容movie_name = response.cssselect(".ranking-box-wrapper li .ranking-top-moive-name")[0].text_content().replace(' ', '').replace('\n', '').encode('utf-8')movie_wish = response.cssselect(".ranking-box-wrapper li .ranking-top-wish")[0].text_content().replace(' ', '').replace('\n', '').encode('utf-8')print movie_name, movie_wishprint '---------------after-----------------'for i in range(len(utf8List)):movie_wish = movie_wish.replace(utf8List[i], numList[i])print movie_name, movie_wishspider = MaoyanSpider()
spider.getNote()