第一条爬虫 - 润新知

第一条爬虫
```
1.
```
from random import random
def printIntro():
print("这个程序模拟两个选手张三和李四的某种竞技比赛")
print("程序运行需要张三和李四的能力值（0-1）")
def getInputs():
a = eval(input("请输入选手张三的能力值(0-1): "))
b = eval(input("请输入选手李四的能力值(0-1): "))
n = eval(input("模拟比赛的场次: "))
return a, b, n
def simNGames(n, probA, probB):
winsA, winsB = 0, 0
for i in range(n):
scoreA, scoreB = simOneGame(probA, probB)
if scoreA > scoreB:
winsA += 1
else:
winsB += 1
return winsA, winsB
def gameOver(a,b):
return a==15 or b==15
def simOneGame(probA, probB):
scoreA, scoreB = 0, 0
serving = "A"
while not gameOver(scoreA, scoreB):
if serving == "A":
if random() < probA:
scoreA += 1
else:
serving="B"
else:
if random() < probB:
scoreB += 1
else:
serving="A"
return scoreA, scoreB
def printSummary(winsA, winsB):
n = winsA + winsB
print("竞技分析开始，共模拟{}场比赛".format(n))
print("选手张三获胜{}场比赛，占比{:0.1%}".format(winsA, winsA/n))
print("选手李四获胜{}场比赛，占比{:0.1%}".format(winsB, winsB/n))
def main():
printIntro()
probA, probB, n = getInputs()
winsA, winsB = simNGames(n, probA, probB)
printSummary(winsA, winsB)
main()

　　
```
2.
```
import requests response = requests.get("http://www.google.cn/") print(type(response)) status_code = response.status_code print(status_code) text = response.text print(text) encoding = response.encoding print(encoding) encoding1 = response.encoding = 'utf-8' print(encoding1) text1 = response.text print("text内容为:{}".format(text1)) print(" ") print("text内容长度为:{}".format(len(text1))) print("content内容长度为:{}".format(len(r.content)))
　　
效果

<class 'requests.models.Response'>
200
<!DOCTYPE html>
<html lang="zh">
<meta charset="utf-8">
<title>Google</title>
<style>
html { background: #fff; margin: 0 1em; }
body { font: .8125em/1.5 arial, sans-serif; text-align: center; }
h1 { font-size: 1.5em; font-weight: normal; margin: 1em 0 0; }
p#footer { color: #767676; font-size: .77em; }
p#footer a { background: url(//www.google.cn/intl/zh-CN_cn/images/cn_icp.gif) top right no-repeat; padding: 5px 20px 5px 0; }
ul { margin: 2em; padding: 0; }
li { display: inline; padding: 0 2em; }
div { -moz-border-radius: 20px; -webkit-border-radius: 20px; border: 1px solid #ccc; border-radius: 20px; margin: 2em auto 1em; max- 650px; min- 544px; }
div:hover, div:hover * { cursor: pointer; }
div:hover { border-color: #999; }
div p { margin: .5em 0 1.5em; }
img { border: 0; }
</style>
<div>
<a href="http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp">
<img src="//www.google.cn/landing/cnexp/google-search.png" alt="Google" width="586" height="257">
</a>
<h1><a href="http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp"><strong id="target">google.com.hk</strong></a></h1>
<p>è¯·æ¶èæä»¬çç½å
</div>
<ul>
<li><a href="http://translate.google.cn/?sourceid=cnhp">ç¿»è¯</a>
</ul>
<p id="footer">©2011 - <a href="http://www.miibeian.gov.cn/">ICPè¯ååB2-20070004å·</a>
<script nonce="0qYFPrpj6kdYUM03_qP12w">
var gcn=gcn||{};gcn.IS_IMAGES=(/images.google.cn/.exec(window.location)||window.location.hash=='#images'||window.location.hash=='images');gcn.HOMEPAGE_DEST='http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp';gcn.IMAGES_DEST='http://images.google.com.hk/imghp?'+'hl=zh-CN&sourceid=cnhp';gcn.DEST_URL=gcn.IS_IMAGES?gcn.IMAGES_DEST:gcn.HOMEPAGE_DEST;gcn.READABLE_HOMEPAGE_URL='google.com.hk';gcn.READABLE_IMAGES_URL='images.google.com.hk';gcn.redirectIfLocationHasQueryParams=function(){if(window.location.search&&/google.cn/.exec(window.location)&&!/webhp/.exec(window.location)){window.location=String(window.location).replace('google.cn','google.com.hk')}}();gcn.replaceHrefsWithImagesUrl=function(){if(gcn.IS_IMAGES){var a=document.getElementsByTagName('a');for(var i=0,len=a.length;i<len;i++){if(a[i].href==gcn.HOMEPAGE_DEST){a[i].href=gcn.IMAGES_DEST}}}}();gcn.listen=function(a,e,b){if(a.addEventListener){a.addEventListener(e,b,false)}else if(a.attachEvent){var r=a.attachEvent('on'+e,b);return r}};gcn.stopDefaultAndProp=function(e){if(e&&e.preventDefault){e.preventDefault()}else if(window.event&&window.event.returnValue){window.eventReturnValue=false;return false}if(e&&e.stopPropagation){e.stopPropagation()}else if(window.event&&window.event.cancelBubble){window.event.cancelBubble=true;return false}};gcn.resetChildElements=function(a){var b=a.childNodes;for(var i=0,len=b.length;i<len;i++){gcn.listen(b[i],'click',gcn.stopDefaultAndProp)}};gcn.redirect=function(){window.location=gcn.DEST_URL};gcn.setInnerHtmlInEl=function(a){if(gcn.IS_IMAGES){var b=document.getElementById(a);if(b){b.innerHTML=b.innerHTML.replace(gcn.READABLE_HOMEPAGE_URL,gcn.READABLE_IMAGES_URL)}}};
gcn.listen(document, 'click', gcn.redirect);
gcn.setInnerHtmlInEl('target');
</script>

ISO-8859-1
utf-8
text内容为:<!DOCTYPE html>
<html lang="zh">
<meta charset="utf-8">
<title>Google</title>
<style>
html { background: #fff; margin: 0 1em; }
body { font: .8125em/1.5 arial, sans-serif; text-align: center; }
h1 { font-size: 1.5em; font-weight: normal; margin: 1em 0 0; }
p#footer { color: #767676; font-size: .77em; }
p#footer a { background: url(//www.google.cn/intl/zh-CN_cn/images/cn_icp.gif) top right no-repeat; padding: 5px 20px 5px 0; }
ul { margin: 2em; padding: 0; }
li { display: inline; padding: 0 2em; }
div { -moz-border-radius: 20px; -webkit-border-radius: 20px; border: 1px solid #ccc; border-radius: 20px; margin: 2em auto 1em; max- 650px; min- 544px; }
div:hover, div:hover * { cursor: pointer; }
div:hover { border-color: #999; }
div p { margin: .5em 0 1.5em; }
img { border: 0; }
</style>
<div>
<a href="http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp">
<img src="//www.google.cn/landing/cnexp/google-search.png" alt="Google" width="586" height="257">
</a>
<h1><a href="http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp"><strong id="target">google.com.hk</strong></a></h1>
<p>请收藏我们的网址
</div>
<ul>
<li><a href="http://translate.google.cn/?sourceid=cnhp">翻译</a>
</ul>
<p id="footer">©2011 - <a href="http://www.miibeian.gov.cn/">ICP证合字B2-20070004号</a>
<script nonce="0qYFPrpj6kdYUM03_qP12w">
var gcn=gcn||{};gcn.IS_IMAGES=(/images.google.cn/.exec(window.location)||window.location.hash=='#images'||window.location.hash=='images');gcn.HOMEPAGE_DEST='http://www.google.com.hk/webhp?hl=zh-CN&sourceid=cnhp';gcn.IMAGES_DEST='http://images.google.com.hk/imghp?'+'hl=zh-CN&sourceid=cnhp';gcn.DEST_URL=gcn.IS_IMAGES?gcn.IMAGES_DEST:gcn.HOMEPAGE_DEST;gcn.READABLE_HOMEPAGE_URL='google.com.hk';gcn.READABLE_IMAGES_URL='images.google.com.hk';gcn.redirectIfLocationHasQueryParams=function(){if(window.location.search&&/google.cn/.exec(window.location)&&!/webhp/.exec(window.location)){window.location=String(window.location).replace('google.cn','google.com.hk')}}();gcn.replaceHrefsWithImagesUrl=function(){if(gcn.IS_IMAGES){var a=document.getElementsByTagName('a');for(var i=0,len=a.length;i<len;i++){if(a[i].href==gcn.HOMEPAGE_DEST){a[i].href=gcn.IMAGES_DEST}}}}();gcn.listen=function(a,e,b){if(a.addEventListener){a.addEventListener(e,b,false)}else if(a.attachEvent){var r=a.attachEvent('on'+e,b);return r}};gcn.stopDefaultAndProp=function(e){if(e&&e.preventDefault){e.preventDefault()}else if(window.event&&window.event.returnValue){window.eventReturnValue=false;return false}if(e&&e.stopPropagation){e.stopPropagation()}else if(window.event&&window.event.cancelBubble){window.event.cancelBubble=true;return false}};gcn.resetChildElements=function(a){var b=a.childNodes;for(var i=0,len=b.length;i<len;i++){gcn.listen(b[i],'click',gcn.stopDefaultAndProp)}};gcn.redirect=function(){window.location=gcn.DEST_URL};gcn.setInnerHtmlInEl=function(a){if(gcn.IS_IMAGES){var b=document.getElementById(a);if(b){b.innerHTML=b.innerHTML.replace(gcn.READABLE_HOMEPAGE_URL,gcn.READABLE_IMAGES_URL)}}};
gcn.listen(document, 'click', gcn.redirect);
gcn.setInnerHtmlInEl('target');
</script>

text内容长度为:3216
content内容长度为:3244

3

　　

4.
```
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, "lxml")
    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[2].string,tds[3].string])

def printUnivList(ulist, num):
    tplt = "{0:^6}	{1:{4}^10}	{2:^10}	{3:^10}"
    print(tplt.format("排名","学校名称","省份","总分",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0],u[1],u[2],u[3],chr(12288)))

def main():
    uinfo = []
    url = "http://www.zuihaodaxue.com/zuihaodaxuepaiming2017.html"
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 30)

main()
```
　　
相关阅读:
Django
C++开源库集合
 单细胞参考文献 single cell
第三章 RNA测序
 第二章基因芯片
 前言转录组
 生物信息学——RNA的剪切过程
 生信研究内容
 测序总结，高通量测序名词
 单端测序，双端测序，基因组计划图谱
原文地址：https://www.cnblogs.com/Glzt/p/12883367.html