def crawler(url):
text = requests.get(url, headers=headers).text
font_face = re.findall('base64,(.*?)\)', text)
with TemporaryFile() as f:
f.write(base64.b64decode(font_face[0]))
f.seek(0)
font = TTFont(f)
# font.saveXML('glided_sky.xml') # 转换成xml
number_list = font.getGlyphOrder()[1:11]
font_map = font.getBestCmap()
rows = BeautifulSoup(text, 'lxml').find_all('div', class_="col-md-1")
scores = []
for row in rows:
numbers = []
for font in row.text.strip():
unicode_str = font.encode('unicode-escape').decode()
sixteen_str = unicode_str.replace('\\u', '0x')
# print(int(sixteen_str, 16))
number = number_list.index(font_map[int(sixteen_str, 16)])
numbers.append(str(number))
scores.append(int(''.join(numbers)))
print(f"第{url.split('=')[-1]}页 合计:{sum(scores)} 明细:{scores}")
return sum(scores)
