Python爬虫和函数调试

一：函数调试

用之前学过的try···except进行调试

def gameover(setA,setB):
    if setA==3 or setB==3:
        return True
    else:
        return False
try:
    a=gameover(7,11)
    print(a)
except:
    print("Error")

　　调试完毕~~~~

结果如下

输入7,8的结果

输入3,4的结果

不输入参数时，得到Error

二：Python爬虫

requests库是一个简洁且简单的处理HTTP请求的第三方库。

get()是对应与HTTP的GET方式，获取网页的最常用方法，可以增加timeout=n 参数，设定每次请求超时时间为n秒

text（）是HTTP相应内容的字符串形式，即url对应的网页内容

content（）是HTTP相应内容的二进制形式

用requests（）打开搜狗主页20次

# -*- coding: utf-8 -*-
"""
Created on Mon May 20 10:20:45 2019

@author: guo'yu'yi
"""

import requests
try:
for i in range(20):
r=get("https://123.sogou.com/")
r.raise_for_status()
r.encoding='utf-8'
print(r)
print(len(r.text))
print(len(r.content))
except:
print("Error")

　结果如下：

获取中国大学排名

直接上代码

import requests
from bs4 import BeautifulSoup
import pandas
# 1. 获取网页内容
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except Exception as e:
        print("Error:", e)
        return ""

# 2. 分析网页内容并提取有用数据
def fillTabelList(soup): # 获取表格的数据
    tabel_list = []      # 存储整个表格数据
    Tr = soup.find_all('tr')
    for tr in Tr:
        Td = tr.find_all('td')
        if len(Td) == 0:
            continue
        tr_list = [] # 存储一行的数据
        for td in Td:
            tr_list.append(td.string)
        tabel_list.append(tr_list)
    return tabel_list

# 3. 可视化展示数据
def PrintTableList(tabel_list, num):
    # 输出前num行数据
    print("{1:^2}{2:{0}^10}{3:{0}^5}{4:{0}^5}{5:{0}^8}".format(chr(12288), "排名", "学校名称", "省市", "总分", "生涯质量"))
    for i in range(num):
        text = tabel_list[i]
        print("{1:{0}^2}{2:{0}^10}{3:{0}^5}{4:{0}^8}{5:{0}^10}".format(chr(12288), *text))

# 4. 将数据存储为csv文件
def saveAsCsv(filename, tabel_list):
    FormData = pandas.DataFrame(tabel_list)
    FormData.columns = ["排名", "学校名称", "省市", "总分", "生涯质量", "培养结果", "科研规模", "科研质量", "顶尖成果", "顶尖人才", "科技服务", "产学研合作", "成果转化"]
    FormData.to_csv(filename, encoding='utf-8', index=False)

if __name__ == "__main__":
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
    html = getHTMLText(url)
    soup = BeautifulSoup(html, features="html.parser")
    data = fillTabelList(soup)
    #print(data)
    PrintTableList(data, 10)   # 输出前10行数据
    saveAsCsv("D:\\python文件\\daxuepaimingRank.csv", data)