爬取腾讯课堂IT-互联网分类的的课程信息存入csv文件

标签（空格分隔）： python

---

from urllib.request import urlopen
from bs4 import BeautifulSoup
#获取IT-互联网分类每页的课程的链接
for i in range(1,35):
    url = \'https://ke.qq.com/course/list?mt=1001&page=\'+str(i)
    html = urlopen(url)
    bs_obj = BeautifulSoup(html,\'html.parser\')
    bs_obj = bs_obj.find(\'ul\',{\'class\':\'course-card-list\'})
    links = bs_obj.find_all(\'a\',{\'class\':\'item-tt-link\'})
    #准备一个文件，先将标题写入的文件中
    with open(\'./tengxu.csv\',\'w\',encoding=\'utf8\') as f:
        f.write(\'课程名称,链接地址,购买人数,好评度,价格\n\')
    #获取每个课程的名称、链接、报名人数、好评度、价格
    for link in links:
        course_name = link.get_text()
        course_link = \'https:\' + link.attrs.get(\'href\')
        course_html = urlopen(course_link)
        bs_objec = BeautifulSoup(course_html,\'html.parser\')
        number_buyer_bs = bs_objec.find(\'span\',{\'class\':\'apply-num js-apply-num\'})
        number_buyer = number_buyer_bs.get_text()
        good_evaluate_bs = bs_objec.find(\'span\',{\'class\',\'rate-num\'})
        good_evaluate = good_evaluate_bs.get_text()
        price_bs = bs_objec.find(\'span\',{\'class\':\'price\'})
        price = price_bs.get_text()
        #将信息写入到文件中
        with open(\'./tengxu.csv\',\'a\',encoding=\'utf8\') as f:
            f.write(course_name)
            f.write(\',\')
            f.write(course_link)
            f.write(\',\')
            f.write(number_buyer)
            f.write(\',\')
            f.write(good_evaluate)
            f.write(\',\')
            f.write(price)
            f.write(\'\n\')