Python实现的飞速中文网小说下载脚本

#!/usr/bin/env python3
# vim:fileencoding=utf-8

import sys
from functools import partial
from string import Template
import argparse
import base64
from urllib.parse import unquote

from lxml.html import fromstring
import requests

from htmlutils import extractText
from termutils import foreach

session = requests.Session()

def main(index, filename='$name-$author.txt', start=0):
 r = session.get(index)
 r.encoding = 'gb18030'
 doc = fromstring(r.text, base_url=index)
 doc.make_links_absolute()
 name = doc.xpath('//div[@class="info"]/p[1]/a/text()')[0]
 author = doc.xpath('//div[@class="info"]/p[1]/span/text()')[0].split()[-1]

 nametmpl = Template(filename)
 fname = nametmpl.substitute(name=name, author=author)
 with open(fname, 'w') as f:
  sys.stderr.write('下载到文件 %s。\n' % fname)
  links = doc.xpath('//div[@class="chapterlist"]/ul/li/a')
  try:
   foreach(links, partial(gather_content, f.write), start=start)
  except KeyboardInterrupt:
   sys.stderr.write('\n')
   sys.exit(130)

 sys.stderr.write('\n')
 return True

def gather_content(write, i, l):
 # curl -XPOST -F bookid=2747 -F chapterid=2098547 'http://www.feisuzw.com/skin/hongxiu/include/fe1sushow.php'
 #   --referer http://www.feisuzw.com/Html/2747/2098547.html
 # tail +4
 # base64 -d
 # sed 's/&#&/u/g'
 # ascii2uni -qaF
 # ascii2uni -qaJ
 # <p> paragraphs
 url = l.get('href')
 _, _, _, _, bookid, chapterid = url.split('/')
 chapterid = chapterid.split('.', 1)[0]
 r = session.post('http://www.feisuzw.com/skin/hongxiu/include/fe1sushow.php', data={
  'bookid': bookid, 'chapterid': chapterid,
 }, headers={'Referer': url})

 text = r.content[3:] # strip BOM
 text = base64.decodebytes(text).replace(b'&#&', br'\u')
 text = text.decode('unicode_escape')
 text = unquote(text)
 text = text.replace('<p>', '').replace('</p>', '\n\n')

 title = l.text
 write(title)
 write('\n\n')
 write(text)
 write('\n')
 return title

if __name__ == '__main__':
 parser = argparse.ArgumentParser(description='下载飞速中文网小说')
 parser.add_argument('url',
           help='小说首页链接')
 parser.add_argument('name', default='$name-$author.txt', nargs='?',
           help='保存文件名模板（支持 $name 和 $author')
 parser.add_argument('-s', '--start', default=1, type=int, metavar='N',
           help='下载起始页位置（以 1 开始）')
 args = parser.parse_args()
 main(args.url, args.name, args.start-1)