Python7个爬虫小案例详解(附源码)上篇

import csv
import requests
import re
import time
 
def main(page):
    url = f'https://tieba.baidu.com/p/7882177660?pn={page}'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'
    }
    resp = requests.get(url,headers=headers)
    html = resp.text
    # 评论内容
    comments = re.findall('style="display:;">                    (.*?)</div>',html)
    # 评论用户
    users = re.findall('class="p_author_name j_user_card" href=".*?" rel="external nofollow"  target="_blank">(.*?)</a>',html)
    # 评论时间
    comment_times = re.findall('楼</span><span class="tail-info">(.*?)</span><div',html)
    for u,c,t in zip(users,comments,comment_times):
        # 筛选数据,过滤掉异常数据
        if 'img' in c or 'div' in c or len(u)>50:
            continue
        csvwriter.writerow((u,t,c))
        print(u,t,c)
    print(f'第{page}页爬取完毕')
 
if __name__ == '__main__':
    with open('01.csv','a',encoding='utf-8')as f:
        csvwriter = csv.writer(f)
        csvwriter.writerow(('评论用户','评论时间','评论内容'))
        for page in range(1,8):  # 爬取前7页的内容
            main(page)
            time.sleep(2)

import requests
from lxml import etree
import re
import pymysql
from time import sleep
from concurrent.futures import ThreadPoolExecutor
 
def get_conn():
    # 创建连接
    conn = pymysql.connect(host="127.0.0.1",
                           user="root",
                           password="root",
                           db="novels",
                           charset="utf8")
    # 创建游标
    cursor = conn.cursor()
    return conn, cursor
 
def close_conn(conn, cursor):
    cursor.close()
    conn.close()
 
def get_xpath_resp(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'}
    resp = requests.get(url, headers=headers)
    tree = etree.HTML(resp.text)  # 用etree解析html
    return tree,resp
 
def get_chapters(url):
    tree,_ = get_xpath_resp(url)
    # 获取小说名字
    novel_name = tree.xpath('//*[@id="info"]/h1/text()')[0]
    # 获取小说数据节点
    dds = tree.xpath('/html/body/div[4]/dl/dd')
    title_list = []
    link_list = []
    for d in dds[:15]:
        title = d.xpath('./a/text()')[0]  # 章节标题
        title_list.append(title)
        link = d.xpath('./a/@href')[0]   # 章节链接
        chapter_url = url +link  # 构造完整链接
        link_list.append(chapter_url)
    return title_list,link_list,novel_name
 
def get_content(novel_name,title,url):
    try:
        cursor = None
        conn = None
        conn, cursor = get_conn()
        # 插入数据的sql
        sql = 'INSERT INTO novel(novel_name,chapter_name,content) VALUES(%s,%s,%s)'
        tree,resp = get_xpath_resp(url)
        # 获取内容
        content = re.findall('<div id="content">(.*?)</div>',resp.text)[0]
        # 对内容进行清洗
        content = content.replace('<br />','\n').replace('&nbsp;',' ').replace('全本小说网 www.qb5.tw，最快更新<a href="https://www.qb5.tw/book_116659/" rel="external nofollow" >宇宙职业选手</a>最新章节！<br><br>','')
        print(title,content)
        cursor.execute(sql,[novel_name,title,content])  # 插入数据
        conn.commit()  # 提交事务保存数据
    except:
        pass
    finally:
        sleep(2)
        close_conn(conn, cursor)  # 关闭数据库
 
 
if __name__ == '__main__':
    # 获取小说名字，标题链接，章节名称
    title_list, link_list, novel_name = get_chapters('https://www.qb5.tw/book_116659/')
    with ThreadPoolExecutor(5) as t:  # 创建5个线程
        for title,link in zip(title_list,link_list):
            t.submit(get_content, novel_name,title,link)  # 启动线程