python编程作业20

[2019301251-李佶骏]

import urllib.request
import xlwt
import re
from bs4 import BeautifulSoup


def jiexi(url):
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36 Edg/100.0.1185.39"
    }
    request = urllib.request.Request(url , headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        print(html)
    except urllib.error.URError as e:
        if hasattr(e , "code"):
            print(e.code)
        if hasattr(e , "reason"):
            print(e.reason)
    return html


def getdata(baseural):
    datalist = []
    c=[]
    for i in range(1 , 51):
        url = baseural + str(i)
        # print(url)
        html = jiexi(url)
        soup = BeautifulSoup(html , "html.parser")  
        for item in soup.find_all('div' , class_="rank_d_list borderB_c_dsh clearfix"):
            data = []
            # print(item)
            item = str(item)

            title = re.findall(name , item)[0]

            zuoz = re.findall(aut , item)[0]  
            # print(zuoz)
            leix = re.findall(cate , item)[0]  
            # print(leix)
            lianjie = re.findall(link , item)[0]  
            # print(lianjie)
            img = re.findall(photo , item)[0]  
            # print(img)
            # 数据加入到列表里
            data.append(title)
            data.append(zuoz)
            data.append(leix)
            data.append(lianjie)
            datalist.append(data)
            c.append(title)
    # print(datalist)
    return (datalist,c) 


def savedata(datalist , filename):
    book = xlwt.Workbook(encoding="utf-8" , style_compression=0)   \
    sheet = book.add_sheet('小说' , cell_overwrite_ok=True)  
    col = ("小说名" , "作者" , "类型" , "小说链接" , "图片链接")
    for i in range(0 , 5):
        sheet.write(0 , i , col[i])
    for i in range(0 , 1000):
        data = datalist[i]
        for j in range(0 , 5):
            sheet.write(i + 1 , j , data[j])
    book.save(filename)


def crawler(books):
    baseural = "http://www.zongheng.com/rank/details.html?rt=1&d=1&p="  
    jiexi(baseural)
    filename = "小说排行榜.xls"
    datalist = getdata(baseural)[1]
    c=getdata(baseural)[2]
    savedata(datalist , filename)
    d=0
    dic={}
    for name in books:
        for i in c:
            if c[i]==name:
                d=d+1
                dic[name]=d
    return print(dic)
    






name = re.compile(r'<div class="rank_d_b_name" title="(.*?)">')
aut = re.compile(r'<div class="rank_d_b_cate" title="(.*?)">')
photo = re.compile(r'src="(.*?)"/>' , re.S)
link = re.compile(r'href="(.*?)" target="_blank">')
cate = re.compile(r'<a target="_blank">(.*?)<')
# print(photo)
if __name__ == "__main__":
    books=input("books:")
    crawler(books)

 

[CSDN-Ada助手]

您可以前往 CSDN问答-Python 发布问题, 以便更快地解决您的疑问