您好,登錄后才能下訂單哦!
這篇文章主要介紹了如何使用Python實現的文軒網爬蟲,具有一定借鑒價值,感興趣的朋友可以參考下,希望大家閱讀完這篇文章之后大有收獲,下面讓小編帶著大家一起了解一下。
具體如下:
encoding=utf8 import pymysql import time import sys import requests import os #捕獲錯誤 import traceback import types #將html實體化 import cgi import warnings reload(sys) sys.setdefaultencoding('utf-8') from pyquery import PyQuery as pq from lxml import etree sys.setdefaultencoding('utf-8') #屏蔽錯誤 warnings.filterwarnings("ignore") #下載圖片 def dowloadPic(imageUrl,filePath): r = requests.get(imageUrl,timeout=60) status=r.status_code if status == 404: return 404 with open(filePath, "wb") as code: code.write(r.content) #根據詳情頁地址抓取數據并插入數據庫 def getData(final_url): file_open=open('./url.txt', 'w') file_open.write(final_url) file_open.close() #鏈接數據庫 conn = pymysql.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='bookinfo', charset='utf8') #設置浮標 cursor = conn.cursor(cursor=pymysql.cursors.DictCursor) #解析詳情頁面 try: detail_url=final_url c=pq(detail_url) head=c('html').attr('xmlns') err='http://www.w3.org/1999/xhtml' err1='http://www.winxuan.com/cms/2016db_sh' if head == err or head == err1: return 'back' except Exception, e: return 'back' i=0 while i<12: text = c('#page').find('.cont').find('li').eq(i).text() text=text.replace(' ','') if 'I S B N' in text: isbn=text.replace('I S B N:','') isbn=isbn.strip() sel='select count(*) from bi_book where isbn ='+isbn cursor.execute(sel) result=cursor.fetchone() count=result['count(*)'] if count != 0 : print u'已存在' return 'back' if 'isbn:' in text : isbn=text.replace('isbn:','') isbn=isbn.strip() sel='select count(*) from bi_book where isbn ='+isbn cursor.execute(sel) result=cursor.fetchone() count=result['count(*)'] if count != 0 : print u'已存在' return 'back' if '作者:' in text : author = text.replace('作者:','') if '出版社:' in text : press_name=text.replace('出版社:','') if '版次:' in text : edition=text.replace('版次:','') if '印次:' in text : impressions=text.replace('印次:','') if '裝幀:' in text : packaging=text.replace('裝幀:','') if '開本:' in text: size=text.replace('開本:','') if '出版時間:' in text: press_time=text.replace('出版時間:','') press_time=press_time.strip() if press_time == '無': press_time='1970-01-01' if '印刷時間:' in text: print_time=text.replace('印刷時間:','') print_time=print_time.strip() if print_time== '無': print_time='1970-01-01' if '頁數:' in text: page_num=text.replace('頁數:','') if '字數:' in text: word_num=text.replace('字數:','') i+=1 if ('author' in locals().keys()) == False: author = '' if ('press_time' in locals().keys()) == False: press_time = '1970-01-01' if ('print_time' in locals().keys()) == False: print_time = '1970-01-01' if ('impressions' in locals().keys()) == False: impressions = '' if ('edition' in locals().keys())== False: edition = '' if ('page_num' in locals().keys())== False: page_num = '' if ('word_num' in locals().keys())== False: word_num = '' if ('packaging' in locals().keys())== False: packaging = '' if ('size' in locals().keys())== False: size = '' if ('press_name' in locals().keys())== False: press_name = '' #暫無圖片地址 none_img='https://cache.yisu.com/upload/information/20200622/113/35179.jpg' #獲取大小圖地址 big_path=c('.info-side').find('.img').find('a').find('img').attr('src') if big_path is None: return 'back' elif big_path == none_img : big_path='' small_path='' else : small_path=big_path.replace('_16','_11') #獲取分類 #先獲取a標簽html ahtml=c('#page').find('.base-nav').eq(0).html() #解析a標簽html cate=pq(ahtml) #獲取分類的最后一個分類 category=cate('a:last').text() #獲取書名 name=c('.info-main').find('.name').eq(0).find('h2').eq(0).text() name=name.strip() #獲取價格 price=c('.info-main').find('.attr').eq(0).find('.price-n').eq(0).find('b').text() price=price.replace('¥','') #循環獲取內容簡介和目錄信息 k=5 while k<12: title=c('#page').find('.title').eq(k).find('.tab').find('h5').text() if '內容簡介' in title: con=c('#page').find('.title').eq(k).nextAll() det=pq(con) content=det('.text-words-1').html() content=content.encode("utf8", "ignore"); if '目錄' in title: con=c('#page').find('.title').eq(k).nextAll() dry=pq(con) directory=dry('.text-words-1').html() directory=directory.encode("utf8", "ignore"); k+=1 #如果內容簡介和目錄沒有的時候指定為空字符串 if ('content' in locals().keys())== False: content = '' if ('directory' in locals().keys())== False: directory = '' details = '內容簡介<br>'+content+'<br><br>目錄<br>'+directory details=cgi.escape(details) #錄入時間 add_time = time.strftime('%Y-%m-%d',time.localtime(time.time())) #下載小圖 #文件根目錄 root_path=sys.path[0] #創建isbn文件夾路徑 root_path=root_path.replace('\\','/') isbn_path=root_path+'/download/'+isbn if big_path != '' and small_path !='' : #創建isbn目錄 if os.path.isdir(isbn_path) ==False : os.mkdir(isbn_path) #組合下載后圖片保存路徑 down_img_small = isbn_path+"/small"+isbn+".jpg" down_img_big = isbn_path+'/big'+isbn+".jpg" #調用下載圖片方法 small_res=dowloadPic(small_path,down_img_small) #大圖保存數據庫路徑 big_res=dowloadPic(big_path,down_img_big) #小圖保存數據庫路徑 if small_res==404 : img_small = 'none-picture/none-small.jpg' else : img_small = 'download/'+isbn+'/small'+isbn+'.jpg' if big_res==404 : img_big = 'none-picture/none-big.jpg' else : img_big = 'download/'+isbn+'/big'+isbn+'.jpg' else : #組合保存數據庫中的圖片路徑 img_small = 'download/'+isbn+'/small'+isbn+'.jpg' img_big = 'download/'+isbn+'/big'+isbn+'.jpg' else : img_big = 'none-picture/none-big.jpg' img_small = 'none-picture/none-small.jpg' source_type = 3 try : #要插入的列表 li=[0,source_type,category,details,detail_url,price,add_time,packaging,print_time,impressions,name,author,press_name,isbn,edition,size,press_time,page_num,word_num,img_big,img_small] #執行sql sql="insert into bi_book (book_id,source_type,category,details,detail_url,price,add_time,packaging,print_time,impressions,name,author,press_name,isbn,edition,size,press_time,page_num,word_num,img_big,img_small) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)" aaa=cursor.execute(sql,li) if aaa==1: print u'插入成功' conn.commit() except Exception, e : return 'back' def winxuan(n): #首頁解析 home_url='http://www.winxuan.com/' h=pq(home_url) #分類導航鏈接 menu=h('.mod-mainmenu').find('dd').find('a').eq(n).attr('href') #print menu #分類書籍首頁 try: mh=pq(menu) except Exception, e : return 'backs' # text=mh('.main').find('a').text() # text=text.encode("GBK", "ignore"); li=[] u=0 while u<248 : detail_urls=mh('.main').find('a').eq(u).attr('href') #將取到所有地址放入到列表當中 li.append(detail_urls) u+=1 #進行列表去重 li=list(set(li)) for final_url in li: try: result=getData(final_url) except Exception, e : continue if result=='back' : continue print 'OK,finished' n=0 while n<58: while n<58: print n string=str(n) file_open=open('./number.txt', 'w') file_open.write(string) file_open.close() res=winxuan(n) n+=1 if res=='backs' : continue
感謝你能夠認真閱讀完這篇文章,希望小編分享的“如何使用Python實現的文軒網爬蟲”這篇文章對大家有幫助,同時也希望大家多多支持億速云,關注億速云行業資訊頻道,更多相關知識等著你來學習!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。