headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
r=requests.get("https://maoyan.com/board/1",headers=headers)
font1_url="http:"+re.findall("url\(\'(\/\/.*?woff)\'\)",r.text,re.M)[0]#创建font目录保存基准字体
if not os.path.exists("font"):font1=requests.get(font1_url,headers=headers) os.mkdir("font") with open("./font/base.woff","wb")as f: f.write(font1.content)

base_font = TTFont('./font/base.woff')
base_dict=[]
for i in range(len(baseFont.getGlyphOrder()[2:])):print(f"对应的数字{i+1}:")w=input()base_dict.append({"code":baseFont.getGlyphOrder()[2:][i],"num":w})

new_font_url="http:"+re.findall("url\(\'(\/\/.*?woff)\'\)",r.text,re.M)[0]
font=requests.get(new_font_url,headers=headers)
with open("new_font.woff","wb")as f:f.write(font.content)
new_font = TTFont('new_font.woff')
new_font_code_list=new_font.getGlyphOrder()[2:]

replace_dic=[]
for i in range(10):news = new_font['glyf'][new_font_code_list[i]]for j in range(10):bases = base_font['glyf'][base_dict[j]["code"]]if news == bases: unicode=new_font_code_list[i].lower().replace("uni","&#x")+";" num= base_dict[j]["num"] replace_dic.append({"code":unicode,"num":num})

org_data=r.text
for i in range(len(replace_dic)):new_data=new_data.replace(replace_dic[i]["code"],replace_dic[i]["num"])

tree=etree.HTML(org_data)
dds=tree.xpath('//dl[@class="board-wrapper"]/dd')
info=[]
for dd in dds:title=dd.xpath('.//p[@class="name"]/a/@title')[0]star=dd.xpath('.//p[@class="star"]/text()')[0].replace("主演：","") time=dd.xpath('.//p[@class="releasetime"]/text()')[0].replace("上映时间：","") realticket=dd.xpath('.//p[@class="realtime"]//text()')[1]+dd.xpath('.//p[@class="realtime"]//text()')[2].strip() totalticket=dd.xpath('.//p[@class="total-boxoffice"]//text()')[1]+dd.xpath('.//p[@class="total-boxoffice"]//text()')[2].strip() info.append({"标题":title,"主演":star,"上映时间":time,"实时票房":realticket,"总票房":totalticket})

import csv
csv_file = open("1325.csv", 'w', newline='')
keys = []
writer = csv.writer(csv_file)
keys = info[1].keys()
writer.writerow(keys)
for dic in info: for key in keys: if key not in dic: dic[key ] = '' writer.writerow(dic.values()) csv_file.close()