正则练习

import re
from urllib.request import urlopen  # 打开一个连接  读取源代码
import ssl

# 干掉数字签名证书
ssl._create_default_https_context = ssl._create_default_https_context


def getPage(url):
    response = urlopen(url)  # 和网页链接
    return response.read().decode("utf-8")  # 返回正常的页面源代码,一大堆html


def parsePage(s):  # s是页面源代码
    ret = re.findall('<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>d+).*?' +
                     '<span class="title">(?P<title>.*?)</span>' +
                     '.*?<span class="rating_num".*?>(?P<rating_num>.*?)</span>.*?' +
                     '<span>(?P<comment_num>.*?)评价</span>', s, re.S)
    return ret


def main(num):
    url = 'https://movie.douban.com/top250?start=%s&filter=' % num
    response_html = getPage(url)  # response_html 是html页面源码
    ret = parsePage(response_html)
    print(ret)


count = 0
for i in range(1):  # 10⻚
    main(count)
    count += 25

写入文件版

import re
from urllib.request import urlopen
import ssl

ssl._create_default_https_context = ssl._create_default_https_context


def getPage(url):
    response = urlopen(url)
    return response.read().decode("utf-8")


def parsePage(s):
    com = re.compile(
        '<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>d+).*?' +
        '<span class="title">(?P<title>.*?)</span>' +
        '.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>' +
        '(?P<comment_num>.*?)评价</span>', re.S)
    ret = com.finditer(s)
    for i in ret:
        yield {
            "id": i.group("id"),
            "title": i.group("title"),
            "rating_num": i.group("rating_num"),
            "comment_num": i.group("comment_num"),
        }


def main(num):
    url = 'https://movie.douban.com/top250?start=%s&filter=' % num
    response_html = getPage(url)
    ret = parsePage(response_html)
    f = open("move", "a", encoding="utf-8")

    for obj in ret:
        # print(obj)
        data = str(obj)
        f.write(data + "
")


count = 0
for i in range(5):
    main(count)