利用python爬取豆瓣最受歡迎的影評50條的相關資訊，包括標題,作者,影片名,影片詳情連結,推薦級,迴應數,影評連結,影評,有用數這9項內容，然後將爬取的資訊寫入Excel表中。具體程式碼如下：

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys

reload(sys)
sys.setdefaultencoding('utf8')
from bs4 import BeautifulSoup
import re
import urllib2
import xlwt


# 得到頁面全部內容
def askURL(url):
    request = urllib2.Request(url)  # 傳送請求
 

    try:
        response = urllib2.urlopen(request)  # 取得響應
        html = response.read()  # 獲取網頁內容
        # print html
    except urllib2.URLError, e:
        if hasattr(e, "code"):
            print e.code
        if hasattr(e, "reason"):
            print e.reason
    return html


# 獲取相關內容
def
 
 getData(baseurl):
    # 找到評論標題
    pattern_title = re.compile(r'<a href=".*/review/\d+/">(.+)</a>')
    # 找到評論全文連結
    pattern_link = re.compile(r'<a href="(.*/review/\d+/)">.+</a>')
    # 找到作者
    pattern_author = re.compile(r'<a.+property="v:reviewer">(.+)</a>')
    # 找到評論的影片和影評詳情連結
 

    pattern_subject_link = re.compile(r'<a class="subject-img" href="(.+subject.+)"> <img.+title="(.+)".+>')
    # 找到推薦等級
    pattern_star = re.compile(r'<span.+property="v:rating" title="(.+)"></span>')
    # 找到迴應數
    pattern_response = re.compile(r'<a class="reply" href=".*/review/\d+/#comments">(\d+)迴應</a>')
    # 找到有用數
    pattern_use = re.compile(r'<span id="r-useful_count-\d+">\s*(\d+)\s*</span>')
    remove = re.compile(r'<.+?>')  # 去除標籤
    datalist = []
    for i in range(0, 5):
        url = baseurl + str(i * 10)  # 更新url
        # print url
        html = askURL(url)
        # print html
        soup = BeautifulSoup(html, "html.parser")
        # 找到每一個影評項
        for item in soup.find_all('div', class_='main review-item'):
            data = []
            item = str(item)  # 轉換成字串
            # print item
            title = re.findall(pattern_title, item)[0]
            # print title
            reviewlink = re.findall(pattern_link, item)[0]
            # print reviewlink
            data.append(title)  # 新增標題
            author = re.findall(pattern_author, item)[0]
            # print author
            data.append(author)  # 新增作者
            list_subject_link = re.findall(pattern_subject_link, item)[0]
            moviename = list_subject_link[1]
            # print moviename
            movielink = list_subject_link[0]
            # print movielink
            data.append(moviename)  # 新增片名
            data.append(movielink)  # 新增影片連結
            star = re.findall(pattern_star, item)
            if len(star) != 0:
                star = star[0]
            else:  # 可能沒有star
                star = ''
            # print star
            data.append(star)  # 新增推薦等級
            response = re.findall(pattern_response, item)[0]
            # print response
            data.append(response)  # 添加回應數
            data.append(reviewlink)  # 新增評論正文連結
            use = re.findall(pattern_use, item)[0]
            # print use
            content = askURL(reviewlink)
            content = BeautifulSoup(content, "html.parser")
            desc = content.find_all('div', id='link-report')[0]
            desc = re.sub(remove, '', str(desc))  # 去掉標籤
            # print desc
            data.append(desc)  # 新增評論正文
            data.append(use)  # 新增有用數
            # print data
            datalist.append(data)
    return datalist


# 將相關資料寫入excel中
def saveData(datalist, savepath):
    book = xlwt.Workbook(encoding='utf-8', style_compression=0)
    sheet = book.add_sheet('豆瓣最受歡迎影評', cell_overwrite_ok=True)
    col = ('標題', '作者', '影片名', '影片詳情連結', '推薦級', '迴應數', '影評連結', '影評', '有用數')
    for i in range(0, 9):
        sheet.write(0, i, col[i])  # 列名
    for i in range(0, 50):  # 總共50條影評
        data = datalist[i]
        for j in range(0, 9):
            sheet.write(i + 1, j, data[j])  # 資料
    book.save(savepath)  # 儲存


def main():
    baseurl = 'http://movie.douban.com/review/best/?start='
    datalist = getData(baseurl)
    savapath = u'豆瓣最受歡迎影評.xlsx'
    saveData(datalist, savapath)
    print 'done'


main()

Excel部分內容如下：

國家代表的影評正文如下：