1.注冊中國大學MOOC
2.選擇北京理工大學嵩天老師的《Python網絡爬蟲與信息提取》MOOC課程
3.學習完成第0周至第4周的課程內容,並完成各周作業
Requests庫的爬取性能分析
(1)京東商品頁面的爬取
import requests url = "https://item.jd.com/2967929.html" try: r = requests.get(url) r.raise_for_status() r.encoding = r.apparent_encoding print(r.text[:1000]) except: print("爬取失敗")
(2)亞馬遜商品頁面的爬取
import requests url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y" try: kv = {'user-agent':'Mozilla/5.0'} r = requests.get(url,headers=kv) r.raise_for_status() r.encoding = r.apparent_encoding print(r.text[0:500]) except: print("爬取失敗")
(3)搜索引擎提交接口
(百度)(360)
import requests keyword = "python" try: kv = {'wd':keyword} r = requests.get("http://www.so.com/s",params=kv) #r = requests.get("http://www.baidu.com/s",params=kv) print(r.request.url) r.raise_for_status() #r.encoding = r.apparent_encoding print(len(r.text)) except: print("爬取失敗")
(4)網絡圖片的爬取和儲存
import requests import os url = "http://image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg" root = "E://pics//" path = root + url.split('/')[-1] try: if not os.path.exitsis(root): os.mkdir(root) if not os.path.exitsis(root): r = requests.get(url) with open(path, 'wb') as f: f.write(r.content) f.close() print("文件保存成功") else: print("文件已存在") except: print("爬取失敗")
(5)ip地址歸屬地查詢
import requests url = "http://m.ip138.com/ip.asp?ip=" try: r = requests.get(url+'202.204.80.112') r.raise_for_status() r.encoding = r.apparent_encoding print(r.text[-500:]) except: print("爬取失敗")
(6)100次測試成功所需時間
import requests def getHTMLText(url): try: r=requests.get(url,timeout=30) r.raise_for_status() #如果狀態不是200,引發HTTPError異常 r.encoding = r.apparent_encoding return r.text except: return '產生異常' def time_count(url): import time time_start= time.time() count=1 while True: a=getHTMLText(url) if a != '產生異常': print('第{}次爬取成功'.format(count)) count+=1 if count == 101: break time_end= time.time() print('100次測試成功所需時間',time_end-time_start,'s') if __name__=='__main__': url = 'https://www.baidu.com' time_count(url)
中國大學排名定向爬蟲(優化)
import requests from bs4 import BeautifulSoup import bs4 def getHTMLText(url): try: r = requests.get(url, timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "" def fillUnivList(ulist, html): soup = BeautifulSoup(html, "html.parser") for tr in soup.find('tbody').children: if isinstance(tr, bs4.element.Tag): tds = tr('td') ulist.append([tds[0].string, tds[1].string, tds[3].string]) def printUnivList(ulist, num): tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}" print(tplt.format("排名","學校名稱","總分",chr(12288))) for i in range(num): u=ulist[i] print(tplt.format(u[0],u[1],u[2],chr(12288))) def main(): uinfo = [] url = 'https://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html' html = getHTMLText(url) fillUnivList(uinfo, html) printUnivList(uinfo, 20) # 20 univs main()
淘寶商品比價定向爬蟲:
import requests import re def getHTMLText(url): try: r = requests.get(url, timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "" def parsePage(ilt, html): try: plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html) tlt = re.findall(r'\"raw_title\"\:\".*?\"',html) for i in range(len(plt)): price = eval(plt[i].split(':')[1]) title = eval(tlt[i].split(':')[1]) ilt.append([price , title]) except: print("") def printGoodsList(ilt): tplt = "{:4}\t{:8}\t{:16}" print(tplt.format("序號", "價格", "商品名稱")) count = 0 for g in ilt: count = count + 1 print(tplt.format(count, g[0], g[1])) def main(): goods = '書包' depth = 3 start_url = 'https://s.taobao.com/search?q=' + goods infoList = [] for i in range(depth): try: url = start_url + '&s=' + str(44*i) html = getHTMLText(url) parsePage(infoList, html) except: continue printGoodsList(infoList) main()
股票數據定向爬蟲(優化):
import requests from bs4 import BeautifulSoup import traceback import re def getHTMLText(url, code="utf-8"): try: r = requests.get(url) r.raise_for_status() r.encoding = code return r.text except: return "" def getStockList(lst, stockURL): html = getHTMLText(stockURL, "GB2312") soup = BeautifulSoup(html, 'html.parser') a = soup.find_all('a') for i in a: try: href = i.attrs['href'] lst.append(re.findall(r"[s][hz]\d{6}", href)[0]) except: continue def getStockInfo(lst, stockURL, fpath): count = 0 for stock in lst: url = stockURL + stock + ".html" html = getHTMLText(url) try: if html=="": continue infoDict = {} soup = BeautifulSoup(html, 'html.parser') stockInfo = soup.find('div',attrs={'class':'stock-bets'}) name = stockInfo.find_all(attrs={'class':'bets-name'})[0] infoDict.update({'股票名稱': name.text.split()[0]}) keyList = stockInfo.find_all('dt') valueList = stockInfo.find_all('dd') for i in range(len(keyList)): key = keyList[i].text val = valueList[i].text infoDict[key] = val with open(fpath, 'a', encoding='utf-8') as f: f.write( str(infoDict) + '\n' ) count = count + 1 print("\r當前進度: {:.2f}%".format(count*100/len(lst)),end="") except: count = count + 1 print("\r當前進度: {:.2f}%".format(count*100/len(lst)),end="") continue def main(): stock_list_url = 'https://quote.eastmoney.com/stocklist.html' stock_info_url = 'https://gupiao.baidu.com/stock/' output_file = 'D:/BaiduStockInfo.txt' slist=[] getStockList(slist, stock_list_url) getStockInfo(slist, stock_info_url, output_file) main()
股票數據Scrapy爬蟲
# -*- coding: utf-8 -*- import scrapy import re class StocksSpider(scrapy.Spider): name = "stocks" start_urls = ['https://quote.eastmoney.com/stocklist.html'] def parse(self, response): for href in response.css('a::attr(href)').extract(): try: stock = re.findall(r"[s][hz]\d{6}", href)[0] url = 'https://gupiao.baidu.com/stock/' + stock + '.html' yield scrapy.Request(url, callback=self.parse_stock) except: continue def parse_stock(self, response): infoDict = {} stockInfo = response.css('.stock-bets') name = stockInfo.css('.bets-name').extract()[0] keyList = stockInfo.css('dt').extract() valueList = stockInfo.css('dd').extract() for i in range(len(keyList)): key = re.findall(r'>.*</dt>', keyList[i])[0][1:-5] try: val = re.findall(r'\d+\.?.*</dd>', valueList[i])[0][0:-5] except: val = '--' infoDict[key]=val infoDict.update( {'股票名稱': re.findall('\s.*\(',name)[0].split()[0] + \ re.findall('\>.*\<', name)[0][1:-1]}) yield infoDict
# -*- coding: utf-8 -*- # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html class BaidustocksPipeline(object): def process_item(self, item, spider): return item class BaidustocksInfoPipeline(object): def open_spider(self, spider): self.f = open('BaiduStockInfo.txt', 'w') def close_spider(self, spider): self.f.close() def process_item(self, item, spider): try: line = str(dict(item)) + '\n' self.f.write(line) except: pass return item
settings.py文件中被修改的區域:
# Configure item pipelines # See https://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300, }
4.提供圖片或網站顯示的學習進度,證明學習的過程。
5.寫一篇不少於1000字的學習筆記,談一下學習的體會和收獲。
剛開始對爬蟲僅停留在基礎的位置,並不是很了解。但通過爬蟲的這門入門啟蒙課程,個人覺得非常適合python初學者,復習掌握python基本編程語法后,就可以開始學習這門課程,通過幾周嵩老師的講解和編寫爬蟲實例,驚嘆python語言的魅力所在,高效與快捷增加了我對python爬蟲深入學習的興趣。
一開始需要環境配置,安裝各種第三方模塊等等,有些東西看懂了,但結果自己寫代碼還是很困難,所以其實個人覺得盡量不要系統地去啃一些東西,根據嵩老師課程上的實例,舉一反三,找一些其他的例子入手,這樣反而更容易掌握。因為爬蟲這種技術,既不需要系統的精通一門語言,也不需要多么高深的數據庫技術,從實操中去學習python中零散的知識,可能可以保證每次學到的都是最需要的部分。
在此次課程的學習中特別注意到一個修改User-Agent爬蟲防屏蔽策略。User-Agent是一種最常見的偽裝瀏覽器的手段。User-Agent是指包含瀏覽器信息、操作系統信息等的一個字符串,也稱之為一種特殊的網絡協議。服務器通過它判斷當前訪問對象是瀏覽器、郵件客戶端還是網絡爬蟲。在request.headers里可以查看user-agent,關於怎么分析數據包、查看其User-Agent等信息,這個在前面的文章里提到過。具體方法可以把User-Agent的值改為瀏覽器的方式,甚至可以設置一個User-Agent池(list,數組,字典都可以),存放多個“瀏覽器”,每次爬取的時候隨機取一個來設置request的User-Agent,這樣User-Agent會一直在變化,防止被牆。在爬取中國大學排名出現的問題,,用requests和BeautifulSoup庫是無法獲取它的信息的,其次還要網站robots協議是否符合相關規定。爬取總體分成三個步驟:從網絡上獲取大學排名網頁內容,定義函數數:getHTMLText();提取網頁中信息並放到合適的數據結構定義函數:fillUnivList();利用數據結構展示並輸出結果,定義函數:printUnivList()有了這三個函數,我們可以把程序封裝成這三個模塊,可讀性更好。
使用bs4進行xml解析時,由於每個節點屬性不完全相同,當統一使用一個方法訪問節點屬性的時候一定要加try,防止程序意外中斷;在使用python語言的時候,為了安全,要注意函數的返回值,特別是類型判斷;網頁抓取要用try,動態數據類型盡量也要。對於url請求分析有三點,認真分析頁面結構,查看js響應的動作;借助瀏覽器分析js點擊動作所發出的請求url;將此異步請求的url作為scrapy再次進行抓取。
課程上最后一周還講了Scrapy框架,它是Python開發的一個快速、高層次的屏幕抓取和web抓取框架,用於抓取web站點並從頁面中提取結構化的數據。Scrapy用途廣泛,可以用於數據挖掘、監測和自動化測試。Scrapy吸引人的地方在於它是一個框架,任何人都可以根據需求方便的修改。它也提供了多種類型爬蟲的基類。