Python爬虫代码框架

Python爬虫代码框架

原因

又是因为作业。。。视频：Python网络爬虫与信息提取

代码

1.爬取网页代码框架（requests库）
可以在网页根目录下放置robots.txt来规定爬取规则，如：https://www.jd.com/robots.txt

import requests
def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status() #如果状态不是200，引发HTTPError异常
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"
if __name__ == "__main__":
    url = "http://www.baidu.com"
    print(getHTMLText(url))

#伪装为浏览器
#kv = {'user-agent':'Mozilla/5.0'}
#r = requests.get(url,headers=kv)

2.关键字查询

import requests
keyword = "Python"
try:
    kv = {'wd':keyword}
    r = requests.get("http://www.baidu.com/s",params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")

3.爬取图片代码框架（存在D盘pics目录中）

import requests
import os
url = "https://ss0.baidu.com/-Po3dSag_xI4khGko9WTAnF6hhy/zhidao/pic/item/80cb39dbb6fd5266db76c6d7a918972bd5073697.jpg"
root = "D://pics//"
#给图片在url上的原名
path = root +url.split('/')[-1]
try:
    #如果没有，建文件夹
    if not os.path.exists(root):
        os.mkdir(root)
    #无重名文件
    if not os.path.exists(path):
        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("爬取失败")

4.bs4

from bs4 import BeautifulSoup
soup = BeautifulSoup(demo, "html.parser")
print(soup.prettify())

5.大学排名实例

import requests
from bs4 import BeautifulSoup
import bs4

#得到html代码
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#获取关键信息
def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        #只有bs4.element.Tag类型才会继续，略过字符串类型的子孙
        if isinstance(tr, bs4.element.Tag):
            #find_all()简写
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string])

#打印大学列表
def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)

main()

实例优化（用中文空格代替英文空格）

import requests
from bs4 import BeautifulSoup
import bs4

#得到html代码
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#获取关键信息
def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        #只有bs4.element.Tag类型才会继续，略过字符串类型的子孙
        if isinstance(tr, bs4.element.Tag):
            #find_all()简写
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[2].string])

#打印大学列表
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    #chr(12288) 中文空格
    print(tplt.format("排名","学校名称","总分", 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 = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20)

main()

6.re 正则表达式