python爬虫基础项目--爬取股吧前十页【阅读】【评论】【标题】【作者】【更新时间】

这是一个爬取股吧前十页数据的爬虫

import re, json
import requests


def write_to_json(infos):
    with open('movies.json', 'w', encoding='utf-8') as fp:
        json.dump(infos, fp)


# 解析页面内容
def parse_page(html_str):

    # 测试页面内容是否能拿到
    # print(html_str)
    # 正则筛选页面的原则：缩小匹配范围。
    ul_p = re.compile(r'<ul class="newlist" tracker-eventcode="gb_xgbsy_ lbqy_rmlbdj">(.*?)</ul>', re.S)
    ul_content = ul_p.search(html_str).group()
    cite_p = re.compile(r'<ul class="newlist" tracker-eventcode="gb_xgbsy_ lbqy_rmlbdj">(.*?)</ul>', re.S)
    cite_list = cite_p.findall(ul_content)

    '''
    阅读
    评论
    标题
    作者
    更新时间
    详情页

    '''

    for cite in cite_list:
        cite_q = re.compile(r'<li>(.*?)</li>', re.S)
        cite_list2 = cite_q.findall(cite)
        for cite2 in cite_list2:
            clk_p = re.compile(r'<cite>(.*?)</cite>', re.S)  ###阅读
            clk = clk_p.findall(cite2)
            #阅读数
            read_count = clk[0].strip()
            print(read_count)
            #评论数
            comment = clk[1].strip()
            #标题
            title_p = re.compile(r'.*?class="note">(.*?)</a>',re.S)
            title = title_p.search(cite2).group(1)
            aut_p = re.compile(r'.*?target="_blank"><font>(.*?)</font>')  ###作者
            aut = aut_p.search(cite2).group(1).strip()
            last_p = re.compile(r'<cite class="last">(.*?)</cite>')  ###更新时间
            last = last_p.search(cite2).group(1)
            url_p = re.compile(r'<a href="(.*?)"')  ###详细地址
            url = url_p.search(cite2).group(1)
            # 设置爬取数据
            item = {}
            item['clk'] = read_count
            item['rev'] = comment
            item['sub'] = title
            item['aut'] = aut
            item['last'] = last
            item['url'] = url
            infos.append(item)

    return infos
        # 保存到json文件

def qingqiu():
    for i in range(1,11):
        # 确定基础url
        base_url = f'http://guba.eastmoney.com/default,99_{i}.html'
        headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36',

        }

    response = requests.get(base_url, headers=headers)
    infos = parse_page(response.text)
    return infos

if __name__ == '__main__':
    # infos = []
    # infos = qingqiu()#提取数据，将数据添加到infos中
    # # 将数据写入文件
    # write_to_json(infos)

    infos = json.load(open('movies.json', 'r'))  ###项目会自己创建一个movies
    for item in infos:
        print(item)

==========================================================================
爬取股吧前十页数据的优化版

import requests,re,json
#判空校验
def get_match(match,number):
    if match:
        return match.group(number)
    return ''
def write_to_json(infos):
    with open('guba.json','w',encoding='utf-8') as fp:
        json.dump(infos,fp)

def parse_page(html_str):
    # print(html_str)
    ul_p = re.compile(r' <ul class="newlist"(.*?)</ul>',re.S)
    ul_content = get_match(ul_p.search(html_str),0)
    li_p = re.compile(r'<li>(.*?)</li>', re.S)
    li_contents = li_p.findall(ul_content)
    # print(li_content)
    for li in li_contents:
        #阅读
        infos_p = re.compile(r'<cite>(.*?)</cite>',re.S)
        infos = infos_p.findall(li)
        if len(infos)==2:
            read_num = infos[0].strip()
            comment_num = infos[1].strip()
            title_p = re.compile(r'" title="(.*?)" class=',re.S)
            title = get_match(title_p.search(li),1)
            # print(title)
            href_p = re.compile(r' <a href="(.*?)" title="',re.S)
            href = get_match(href_p.search(li),1)
            # print(href)
            href = 'http://guba.eastmoney.com'+href
            item = {}
            item['read_num'] =read_num
            item['comment_num'] =comment_num
            item['title'] =title
            item['href'] =href
            print(item)
            infos.append(item)

def main():
    base_url = 'http://guba.eastmoney.com/default,99_%s.html'
    headers= {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
    }
    for page in range(1,13):
        response = requests.get(base_url %page ,headers= headers)
        parse_page(response.text)

if __name__ == '__main__':
    infos = []
    main()
    write_to_json(infos)