获取汉典字符地址列表
# -*- coding: utf-8 -*-
# 入re模块
import re
import urllib.request
from bs4 import BeautifulSoup
# 开保存地址的文件
outfile = open("zdurlfile_jibenjieshi", "w")
# 首列表正则表达式
bspattern = re.compile(r"(?:%[^%']{2}){3}")
# 获取部首列表页面
req1 = urllib.request.Request('http://www.zdic.net/z/jbs/')
response1 = urllib.request.urlopen(req1)
index_page1 = response1.read()
# 析得到部首列表
# 试试直接正则表达式提取部首列表
index_page1 = index_page1.decode('utf8')
bslist = re.findall(bspattern, index_page1)
# 换成字列表的地址
# 获取部首列表页面
for bu in bslist:
bu = "http://www.zdic.net/z/jbs/bs/?bs=" + bu
reqb = urllib.request.Request(bu)
reqb.add_header('Referer', 'http://www.zdic.net/z/jbs/')
responseb = urllib.request.urlopen(reqb)
index_z = responseb.read()
# 分析得到字列表
index_z = index_z.decode('utf8')
zlist = re.findall(r"/z/[^']*?\.htm", index_z)
for uz in zlist:
url = "http://www.zdic.net/" + uz
# 存入文件
outfile.write(url + '\n')
# 数不能为叠加器
print(uz)
outfile.close()
