零基礎學習Python爬蟲

# -*- codeing = utf-8 -*-
from bs4 import BeautifulSoup  # 網(wǎng)頁解析，獲取數(shù)據(jù)
import re  # 正則表達式，進行文字匹配`
import urllib.request, urllib.error  # 制定URL，獲取網(wǎng)頁數(shù)據(jù)
import xlwt  # 進行excel操作
#import sqlite3  # 進行SQLite數(shù)據(jù)庫操作

findLink = re.compile(r'a href="(.*?)" rel="external nofollow"  rel="external nofollow" >')  # 創(chuàng)建正則表達式對象，標售規(guī)則   影片詳情鏈接的規(guī)則
findImgSrc = re.compile(r'img.*src="(.*?)"', re.S)
findTitle = re.compile(r'span class="title">(.*)/span>')
findRating = re.compile(r'span class="rating_num" property="v:average">(.*)/span>')
findJudge = re.compile(r'span>(\d*)人評價/span>')
findInq = re.compile(r'span class="inq">(.*)/span>')
findBd = re.compile(r'p class="">(.*?)/p>', re.S)




def main():
    baseurl = "https://movie.douban.com/top250?start="  #要爬取的網(wǎng)頁鏈接
    # 1.爬取網(wǎng)頁
    datalist = getData(baseurl)
    savepath = "豆瓣電影Top250.xls"    #當前目錄新建XLS，存儲進去
    # dbpath = "movie.db"              #當前目錄新建數(shù)據(jù)庫，存儲進去
    # 3.保存數(shù)據(jù)
    saveData(datalist,savepath)      #2種存儲方式可以只選擇一種
    # saveData2DB(datalist,dbpath)



# 爬取網(wǎng)頁
def getData(baseurl):
    datalist = []  #用來存儲爬取的網(wǎng)頁信息
    for i in range(0, 10):  # 調(diào)用獲取頁面信息的函數(shù)，10次
        url = baseurl + str(i * 25)
        html = askURL(url)  # 保存獲取到的網(wǎng)頁源碼
        # 2.逐一解析數(shù)據(jù)
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div', class_="item"):  # 查找符合要求的字符串
            data = []  # 保存一部電影所有信息
            item = str(item)
            link = re.findall(findLink, item)[0]  # 通過正則表達式查找
            data.append(link)
            imgSrc = re.findall(findImgSrc, item)[0]
            data.append(imgSrc)
            titles = re.findall(findTitle, item)
            if (len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("/", "")  #消除轉義字符
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')
            rating = re.findall(findRating, item)[0]
            data.append(rating)
            judgeNum = re.findall(findJudge, item)[0]
            data.append(judgeNum)
            inq = re.findall(findInq, item)
            if len(inq) != 0:
                inq = inq[0].replace("。", "")
                data.append(inq)
            else:
                data.append(" ")
            bd = re.findall(findBd, item)[0]
            bd = re.sub('br(\s+)?/>(\s+)?', "", bd)
            bd = re.sub('/', "", bd)
            data.append(bd.strip())
            datalist.append(data)

    return datalist


# 得到指定一個URL的網(wǎng)頁內(nèi)容
def askURL(url):
    head = {  # 模擬瀏覽器頭部信息，向豆瓣服務器發(fā)送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122  Safari / 537.36"
    }
    # 用戶代理，表示告訴豆瓣服務器，我們是什么類型的機器、瀏覽器（本質上是告訴瀏覽器，我們可以接收什么水平的文件內(nèi)容）

    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html


# 保存數(shù)據(jù)到表格
def saveData(datalist,savepath):
    print("save.......")
    book = xlwt.Workbook(encoding="utf-8",style_compression=0) #創(chuàng)建workbook對象
    sheet = book.add_sheet('豆瓣電影Top250', cell_overwrite_ok=True) #創(chuàng)建工作表
    col = ("電影詳情鏈接","圖片鏈接","影片中文名","影片外國名","評分","評價數(shù)","概況","相關信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])  #列名
    for i in range(0,250):
        # print("第%d條" %(i+1))       #輸出語句，用來測試
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])  #數(shù)據(jù)
    book.save(savepath) #保存

# def saveData2DB(datalist,dbpath):
#     init_db(dbpath)
#     conn = sqlite3.connect(dbpath)
#     cur = conn.cursor()
#     for data in datalist:
#             for index in range(len(data)):
#                 if index == 4 or index == 5:
#                     continue
#                 data[index] = '"'+data[index]+'"'
#             sql = '''
#                     insert into movie250(
#                     info_link,pic_link,cname,ename,score,rated,instroduction,info)
#                     values (%s)'''%",".join(data)
#             # print(sql)     #輸出查詢語句，用來測試
#             cur.execute(sql)
#             conn.commit()
#     cur.close
#     conn.close()


# def init_db(dbpath):
#     sql = '''
#         create table movie250(
#         id integer  primary  key autoincrement,
#         info_link text,
#         pic_link text,
#         cname varchar,
#         ename varchar ,
#         score numeric,
#         rated numeric,
#         instroduction text,
#         info text
#         )
#
#
#     '''  #創(chuàng)建數(shù)據(jù)表
#     conn = sqlite3.connect(dbpath)
#     cursor = conn.cursor()
#     cursor.execute(sql)
#     conn.commit()
#     conn.close()

# 保存數(shù)據(jù)到數(shù)據(jù)庫







if __name__ == "__main__":  # 當程序執(zhí)行時
    # 調(diào)用函數(shù)
     main()
    # init_db("movietest.db")
     print("爬取完畢！")

  for i in range(0, 10):  # 調(diào)用獲取頁面信息的函數(shù)，10次
        url = baseurl + str(i * 25)

baseurl = "https://movie.douban.com/top250?start="

def askURL(url):
    head = {  # 模擬瀏覽器頭部信息，向豆瓣服務器發(fā)送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122  Safari / 537.36"
    }
    # 用戶代理，表示告訴豆瓣服務器，我們是什么類型的機器、瀏覽器（本質上是告訴瀏覽器，我們可以接收什么水平的文件內(nèi)容）

    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html

  html = response.read().decode("utf-8")

findLink = re.compile(r'a href="(.*?)" rel="external nofollow"  rel="external nofollow" >')  # 創(chuàng)建正則表達式對象，標售規(guī)則   影片詳情鏈接的規(guī)則
findImgSrc = re.compile(r'img.*src="(.*?)"', re.S)
findTitle = re.compile(r'span class="title">(.*)/span>')
findRating = re.compile(r'span class="rating_num" property="v:average">(.*)/span>')
findJudge = re.compile(r'span>(\d*)人評價/span>')
findInq = re.compile(r'span class="inq">(.*)/span>')
findBd = re.compile(r'p class="">(.*?)/p>', re.S)

    # 3.保存數(shù)據(jù)
    saveData(datalist,savepath)      #2種存儲方式可以只選擇一種
    # saveData2DB(datalist,dbpath)

def saveData(datalist,savepath):
    print("save.......")
    book = xlwt.Workbook(encoding="utf-8",style_compression=0) #創(chuàng)建workbook對象
    sheet = book.add_sheet('豆瓣電影Top250', cell_overwrite_ok=True) #創(chuàng)建工作表
    col = ("電影詳情鏈接","圖片鏈接","影片中文名","影片外國名","評分","評價數(shù)","概況","相關信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])  #列名
    for i in range(0,250):
        # print("第%d條" %(i+1))       #輸出語句，用來測試
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])  #數(shù)據(jù)
    book.save(savepath) #保存

   sheet = book.add_sheet('豆瓣電影Top250', cell_overwrite_ok=True) #創(chuàng)建工作表
    col = ("電影詳情鏈接","圖片鏈接","影片中文名","影片外國名","評分","評價數(shù)","概況","相關信息")