爬虫大作业

最新推荐文章于 2025-09-09 16:17:25 发布

weixin_30412013

最新推荐文章于 2025-09-09 16:17:25 发布

阅读量106

点赞数

CC 4.0 BY-SA版权

文章标签：爬虫 python

原文链接：http://www.cnblogs.com/www924121851/p/8970982.html

本文介绍了一种使用Python爬取网易人间记事栏目文章的方法，并统计了常见词汇出现频率。通过requests获取网页内容，利用BeautifulSoup解析，再通过正则表达式过滤常用虚词后，使用jieba进行分词处理，最终统计并输出了高频词汇。

def get_content_info(content_url):
    res = requests.get(content_url)
    res.encoding = 'gbk'
    soup = BeautifulSoup(res.text, 'html.parser')
    return soup.select('#endText')[0].text


def get_page_info(page_url):
    res = requests.get(page_url)
    res.encoding = 'gbk'
    soup = BeautifulSoup(res.text, 'html.parser')
    json_str = soup.select('script')[4].text.replace('var data_list =', '')
    data = demjson.decode(json_str)
    for i in data:
        return get_content_info(i['url'])


def print_words_count(text, top):
    miss_word = "了|他|说|我|你|就|着|又|的|在|是|有|把|到|也|不|都|她|这|便|去|们|还|但|一个|和|却|里|来|要|没|很|\"" \
                "|那|么|一|将|呢|起|于|上|只|得|而|而且|对|所以|见|些|才|从|过|被|并|时|且|给|道|虽然|可以|出|;|="
    text = re.sub("[\s+\.\!\/_\",$%^*+—()?【】“《；》”！\-：，。？、~@#￥%……&*（）]+", "", text)
    text = re.sub(miss_word + '+', "", text)
    words = list(jieba.cut(text))
    key_words = {}
    for i in set(words):  # 统计出词频
        key_words[i] = words.count(i)
    sort_word = sorted(key_words.items(), key=lambda d: d[1], reverse=True)  # 排序
    for j in range(top):  # 输出
        print(sort_word[j])


cn = ''
url = 'http://renjian.163.com/special/renjian_jishi/'
res = requests.get(url)
res.encoding = 'gbk'
soup = BeautifulSoup(res.text, 'html.parser')
page = int(soup.select('.list_page')[0].select('a')[-2].text)
for p in range(2, page):
    if p < 10:
        cn += get_page_info('http://renjian.163.com/special/renjian_jishi_0{}/'.format(p))
    else:
        cn += get_page_info('http://renjian.163.com/special/renjian_jishi_{}/'.format(p))
print_words_count(cn, 120)