The sixth day of Crawler learning

爬取我爱竞赛网的大量数据

首先获取每一种比赛信息的分类连接

def get_type_url(url):
    web_data = requests.get(web_url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    types = soup.select("#mn_P1_menu li a")
    for type in types:
        print(type.get_text())
        get_num(type.get("href"))

而后获取每个分类链接中的总页数

def get_num(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    num = soup.select(".pg span")
    # 部分页面没有分页只有一页，须要分类一下
    if(num!=[]):
        i = int(num[0].get_text().split(" ")[2])
        for w in range(1, i):
            print("第"+str(w)+"页")
            urls = url + "index.php?page={}".format(str(w))
            get_message_url(urls)
    else:
        get_message_url(url)

最后获取每一页中各个比赛的信息

def get_message_url(url):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text, 'lxml')
    titles = soup.select(".xld .xs2_tit a")
    views = soup.select("span.chakan")
    post_times = soup.select("div.list_info")
    for title, view, post_time in zip(titles, views, post_times):
        data = {
            "标题": title.get_text(),
            "浏览量": view.get_text().strip(),
            "发布时间": post_time.get_text().strip().split(" ")[0],
            "连接": title.get("href")
       }
        print(data)