python 爬取豆瓣網(wǎng)頁的示例

import urllib.request

def askURL(url):
    head = {
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 88.0.4324.182Safari / 537.36"
    }# 模擬瀏覽器的登錄
    request = urllib.request.Request(url,headers=head)
    #將網(wǎng)頁的url和頭部信息封裝至一起
    response = urllib.request.urlopen(request)
    #獲取網(wǎng)頁的html代碼
    html = response.read().decode("utf-8")
    #將獲取的數(shù)據(jù)轉(zhuǎn)化為utf-8格式
    #print(html)    #此步可以實(shí)驗(yàn)一下能否成功爬取網(wǎng)頁的html代碼
    return html

import re
from bs4 import BeautifulSoup

def getData(baseurl):
    datalist = []   #建立一個(gè)存放解析出的數(shù)據(jù)的元組
    for i in range(0,10):
        url = baseurl + str(i*25)
        # 通過以下兩張截圖，我們可以發(fā)現(xiàn)豆瓣將每25部電影分為一頁，共分成了10頁、
        # 而其url的差別僅在最后加了25，故通過該規(guī)律，可將所有10張網(wǎng)頁的url全部獲取
        html = askURL(url)
        soup = BeautifulSoup(html,"html.parser")
        #通過beautifulsoup模塊自帶的html代碼解析器進(jìn)行解析
        #并將解析器解析出的數(shù)據(jù)放至soup中

findlink = re.compile(r'a href="(.*?)" rel="external nofollow" >')  # r表示不受轉(zhuǎn)義字符的影響
#該代碼通過正則表達(dá)式搜尋到所有關(guān)于影片鏈接的數(shù)據(jù)，以下代碼類似
findImgSrc = re.compile(r'img.*src="(.*?)"',re.S) #讓換行符包含在字符中
findtitle = re.compile(r'span class="title">(.*)/span>')
findscore = re.compile(r'span class="rating_num" property="v:average">(.*)/span>')
findjudge = re.compile(r'span>(\d*)人評價(jià)/span>')
findinq = re.compile(r'span class="inq">(.*)/span>')
findbd = re.compile(r'p class="">(.*?)/p>',re.S)

        for item in soup.find_all("div",class_="item"):
        #提取所有class為“item”的div模塊，并通過for循環(huán)一步步處理
            data = []
            item = str(item) #將item轉(zhuǎn)化為字符串類型
            link = re.findall(findlink,item)[0]
            #通過影片詳情鏈接的正則表達(dá)式抽取數(shù)據(jù)
            data.append(link)
            #存放至data列表中
            ImgSrc = re.findall(findImgSrc,item)[0]
            data.append(ImgSrc)
            title = re.findall(findtitle,item)
            if len(title)==2:
                #如果影片有多個(gè)名稱，則分別進(jìn)行存儲(chǔ)
                ctitle = title[0]
                data.append(ctitle)
                otitle = title[1].replace("/","")
                data.append(otitle)
            else:
                data.append(title[0])
                data.append(" ")
            score = re.findall(findscore,item)
            data.append(score)
            judge = re.findall(findjudge,item)
            data.append(judge)
            inq = re.findall(findinq,item)
            if len(inq)!=0:
                inq = inq[0].replace("。","")
                data.append(inq)
            else:
                data.append("")
                #若有影片詳情，則輸出；若沒有，則輸出為空
            bd = re.findall(findbd,item)[0]
            bd = re.sub('br(\s+)?/>(\s+)?'," ",bd)
            bd = re.sub('/'," ",bd)
            data.append(bd.strip())   # 去掉前后空格

            datalist.append(data)
    print(datalist)
    return datalist

import xlwt

def savepath(datalist):
    workbook = xlwt.Workbook(encoding="utf-8")
 #創(chuàng)建以utf-8格式編碼的一個(gè)workbook對象，該對象最后能保存為excel表格
    worksheet = workbook.add_sheet("sheetwdy")
 #創(chuàng)建工作表“sheetwdy”
    col = ("電影詳情鏈接", "圖片鏈接", "影片中文名", "影片外國名", "評分", "評價(jià)數(shù)", "概況", "相關(guān)信息")
 #創(chuàng)建一個(gè)元組
    for i in range(0, 8):
        worksheet.write(0, i, col[i])  
 # 將我們剛定義的元組中的信息寫入excel表的第一行
    for i in range(0, 250):
        print("第%d條" % (i + 1))
        data = datalist[i]
        for j in range(0, 8):
            worksheet.write(i + 1, j, data[j])
 #將解析出的數(shù)據(jù)通過for循環(huán)一條條導(dǎo)入excel表中
    workbook.save("豆瓣250.xls")
 #將該excel表進(jìn)行保存