day23-2018-11-16-Re 正则表达式

import re

# res = re.search("e", "alex and exp") # 搜索. 搜到结果就返回
# print(res.group())

# res = re.match("w+", "alex is not a good man") #  从头匹配.  如果匹配到了。 就返回
# print(res.group())

# lst = re.findall("w+", "alex and exo")
# print(lst)

# it = re.finditer("w+", "mai le fo leng")
# for el in it:
#     print(el.group())
#
# # 这个分组是优先级
# lst = re.findall(r"www.(baidu|oldboy).com", "www.oldboy.com")
# print(lst)
#
# # (?: )  去掉优先级
# lst = re.findall(r"www.(?:baidu|oldboy).com", "www.oldboy.com")
# print(lst)

# 加了括号。 split会保留你切的刀
lst = re.split("([ab])", "alex is not a sb, no he is a big sb") # 根据正则表达式进行切割
print(lst)
#
# # 替换
# res = re.sub(r"d+", "_sb_", "alex333wusir666taibai789ritian020feng")
# print(res)
#
# # 替换。 返回的结果带有次数
# res = re.subn(r"d+", "_sb_", "alex333wusir666taibai789ritian020feng")
# print(res)

# a = eval("1+3+5+6")
# print(a)

# code = "for i in range(10):print(i)"
# c = compile(code, "", "exec") # 编译代码
# exec(c)

# obj = re.compile(r"alex(?P<name>d+)and") # 把正则表达式预加载
# res = obj.search("alex250andwusir38ritian2")
# print(res.group())
# print(res.group("name"))

from urllib.request import urlopen
import re

# url = "https://www.dytt8.net/html/gndy/dyzz/20181114/57791.html"
# content = urlopen(url).read().decode("gbk")
# # print(content)
#
# obj = re.compile(r'<div id="Zoom">.*?译　　名(?P<yiming>.*?)<br />◎片　　名(?P<pianming>.*?)<br />◎年　　'
#                  r'代(?P<nian>.*?)<br />.*?<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<url>.*?)">', re.S) # re.S 去掉.的换行
#
# res = obj.search(content)
# print(res.group("yiming"))
# print(res.group("pianming"))
# print(res.group("nian"))
# print(res.group("url"))

obj = re.compile(r'<div class="item">.*?<spanclass="title">(?P<name>.*?)</span>.*?导演: (?P<daoyan>.*?)&nbsp;&nbsp;&nbsp;.*?<span class="rating_num" property="v:average">(?P<fen>.*?)</span>.*?<span>(?P<ren>.*?)人评价</span>', re.S)


def getContent(url):
    content = urlopen(url).read().decode("utf-8")
    return content

def parseContent(content):
    it = obj.finditer(content) # 把页面中所有匹配的内容进行匹配. 返回迭代器
    for el in it:
        yield {
            "name":el.group("name"),
            "daoyan":el.group("daoyan"),
            "ren":el.group("ren"),
            "fen":el.group("fen")
        }




for i in range(10):
    url = "https://movie.douban.com/top250?start=%s&filter=" % i*25
    g = parseContent(getContent(url))
    f = open("movie.txt", mode="a", encoding="utf-8")
    for el in g:
        f.write(str(el)+"
")
    f.close()