采用BeautifulSoup&&pqQuery&&xpath三种方法爬取电影详情页

采用三个框架BeautifulSoup&&pqQuery&&xpath，爬取知名的电影网页

主要是想体验这三种框架爬同一个网页的不同。

当然具体的不同我也说不清道不明 只能是体验了一把

以下代码都是本人亲自撸

如图所示，四个位置。分别爬取 电影名字 -> 电影类别 ->  上映时间 -> 电影评分

以及点击电影名称获取特定电影的电影详情页面，如下图所示

 

1. BeautifulSoup

def save_demo_bs4():
    """
    :return: 采用BeautifulSoup 框架爬取单页中每部电影的名称, 类别,  评分, 上映时间等信息
    """
    url = 'https://ssr1.scrape.center'
    import re
    from bs4 import BeautifulSoup
    html = requests.get(url).text
    soup = BeautifulSoup(html, 'lxml')
    dict = []
    ret = soup.find_all(class_=re.compile("el-card item m-t is-hover-shadow"))  # 找到所有的class属性为当前属性的文本
    for ret_ in ret:
        dict_ = {}
        title_ = ret_.find_all(class_=re.compile('name'))
        xiangqing_url = url + title_[0].attrs['href']  # 得到单页中每部电影的详情页面
        title_ = [i.text.replace('\n', "") for i in title_][0]
        categories_ = ret_.find_all(class_=re.compile('categories'))
        sy_date_ = ret_.find_all(class_=re.compile('m-v-sm info'))
        pingfen_ = ret_.find_all(class_=re.compile('score m-t-md m-b-n-sm'))
        pingfen_ = [i.string.replace('\n', '').replace(' ', '') for i in pingfen_][0]
        dict_['标题'] = title_
        categories_ = [i.text.replace('\n', ' ') for i in categories_]
        dict_['类别'] = categories_
        sy_date_ = [i.text.replace('\n', '') for i in sy_date_][1]
        dict_['上映时间'] = sy_date_
        dict_['评分'] = float(pingfen_)
        xiangqin_html = requests.get(xiangqing_url).text
        soup_xiangqin = BeautifulSoup(xiangqin_html, 'lxml')
        ret__ = soup_xiangqin.find_all(class_=re.compile("drama"))  # 找到所有的class属性为当前属性的文本
        for x in ret__:
            for idx, y in enumerate(x.children):
                if idx == 2:
                    xiangqing = y.text.replace('\n', '').replace(' ', '')
        dict_['电影详情'] = xiangqing
        dict.append(dict_)

代码的运行效果图如下

2. XPATH

def save_demo_xpath():
    """
    :return: 采用xpath框架爬取单页中每部电影的名称, 类别,  评分, 上映时间等信息
    """
    url = 'https://ssr1.scrape.center'
    import requests
    from lxml import etree
    html = requests.get(url).text
    html = etree.HTML(html)
    title_xxpath = '//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[2]/a/h2'
    title_xxpath = '{page}'
    dict = []
    for i in range(10):
        dict_ = {}
        title_xxpath = '//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[2]/a/h2'.format(page=i + 1)
        title = html.xpath(title_xxpath)
        title_ = [i.text for i in title][0]
        category_xxpath = '//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[2]/div[1]'.format(page=i + 1)
        category_ = html.xpath(category_xxpath)
        category_ = [i.xpath('./button/span/text()') for i in category_][0]
        sy_date_xxpath = '//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[2]/div[2]/span[3]'.format(page=i + 1)
        sy_date_ = html.xpath(sy_date_xxpath)
        sy_date_ = [i.text for i in sy_date_][0]
        pingfen_xxpath = '//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[3]/p[1]'.format(page=i + 1)
        pingfen_ = html.xpath(pingfen_xxpath)
        pingfen_ = [i.text.replace("\n", "").replace(" ", "") for i in pingfen_][0]
        dict_['类别'] = category_
        dict_['标题'] = title_
        dict_['上映时间'] = sy_date_
        dict_['评分'] = pingfen_
        xiangqing_url_ = html.xpath('//*[@id="index"]/div[1]/div[1]/div[{page}]/div/div/div[2]'.format(page=i+1))
        xiangqing_url_ = url + [i.xpath('./a/@href') for i in xiangqing_url_][0][0]
        html_xiangqin = requests.get(xiangqing_url_).text
        html_xiangqin = etree.HTML(html_xiangqin)
        xiangqing = html_xiangqin.xpath('//*[@id="detail"]/div[1]/div/div/div[1]/div/div[2]/div[4]/p')
        dict_['电影详情'] = [i.text.replace('\n', '').replace(' ', '') for i in xiangqing][0]
        dict.append(dict_)
        print(dict_)
    print(dict)

代码效果图

 

3.pqQuery 

def save_demo_pq():
    """
    :return: 采用pyQuery 框架爬取单页中每部电影的名称, 类别,  评分, 上映时间等信息
    """
    url = 'https://ssr1.scrape.center'
    from pyquery import PyQuery as pq
    import requests

    html = requests.get(url).text
    doc = pq(html)
    items = doc('.el-card .el-card__body .el-row ').items()
    dict = []
    for item in items:
        dict_ = {}
        title = item.find('a > h2').text()
        categories = item.find('.categories .el-button span').items()
        cate_list = [i.text() for i in categories]
        sy_date = item.find('.m-v-sm.info')
        sy_date = [i.text() for i in sy_date('.m-v-sm span').items()][-1]
        pingfen = item.find('.el-col .score').items()
        pingfen = [i.text() for i in pingfen][0]
        dict_['评分'] = float(pingfen)
        dict_['类别'] = cate_list
        dict_['标题'] = title
        dict_['上映时间'] = str(sy_date).replace("上映", "").replace(" ", "")
        dict.append(dict_)
        xiangqing_utl_ = item.find('a').attr('href')
        xiangqing_utl_ = url + xiangqing_utl_
        html_xiangqing = requests.get(xiangqing_utl_).text
        doc_xiangqing = pq(html_xiangqing)
        xiangqing = [i.find('p').text() for i in doc_xiangqing.find('.drama').items()][0]
        dict_['影片详情'] = xiangqing
        print(dict_)
    print(dict)

代码效果图

综合来讲 我觉得pqQuery 用起来更顺手一点 

完毕