Python學爬蟲的課程備忘
阿新 • • 發佈:2018-11-23
學習慕課網的北京理工大學的嵩天老師關於爬蟲的授課,講的非常好。為了幫自己整理知識,特意在此備忘。
爬取百度的首頁
至於版權,那還是算嵩老師的。
#CrawUnivRankingB.py 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()
#!/usr/bin/python # -*- coding: <encoding name> -*- import requests def getHTMLText(url): try: r = requests.get(url,timeout = 30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return '網路錯誤' if __name__ == '__main__': url = 'http://www.baidu.com' print(getHTMLText(url))