玩玩python爬虫，爬取图片，文字，视频，音频

爬取天气 并存在数据库

#!/usr/bin/python
# -*- coding: utf-8 -*-
import pymysql
import requests
from bs4 import BeautifulSoup

db = pymysql.connect(
    host='localhost',
    port=3306,
    user='root',
    passwd='root',
    db='mysql',
    use_unicode=True,
    charset="utf8"
)
cursor = db.cursor()


def downdata(url):
    hd = {
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"}
    req = requests.get(url, headers=hd)
    # req.encoding = 'utf-8'
    soup = BeautifulSoup(req.text, 'html.parser')
    da_new = soup.find_all('li', class_='ndays-item png-fix cf')

    for da in da_new:
        day = da.find('div', class_='td td2').find('p', class_='p1')
        week = da.find('div', class_='td td2').find('p', class_='p2')
        wd = da.find('div', class_='td td5').find('p', class_='p1')
        fl = da.find('div', class_='td td5').find('p', class_='p2')
        f2 = da.find('div', class_='td td3').find('div')['title']
        print('今天是' + day.text + ',' + '星期' + week.text + ',' + '温度' + wd.text + ',' + '风力' + fl.text + ',' + '天气' + f2)
        sql = "INSERT INTO tianiq(day1,week1, wd, fl, air)  VALUES ('%s','%s','%s','%s','%s')" % (day.text, week.text, wd.text, fl.text, f2)
        print(sql)
        cursor.execute(sql)
        db.commit()

downdata('http://tianqi.sogou.com/shenyang/15/')

爬取漫画

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import re
import urllib.request
def gethtml(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
    req = urllib.request.Request(url=url, headers=headers)
    html = urllib.request.urlopen(req).read()
    return html
def getimg(html):
    reg = r'src="(.*?\.jpg)"'
    img=re.compile(reg)
    html=html.decode('utf-8')#python3
    imglist=re.findall(img,html)
    x = 0
    for imgurl in imglist:
        urllib.request.urlretrieve(imgurl,'D:%s.jpg'%x)
        x = x+1
html=gethtml("http://www.tuku.cc/")

print(getimg(html))

调用数据库

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import pymysql

# 打开数据库连接
db = pymysql.connect("localhost", "root", "root", "mysql")
# 使用cursor()方法获取操作游标
cursor = db.cursor()
# SQL 插入语句
sql = "INSERT INTO tianiq(day1, \
week1, wd, fl, air) \
    VALUES ('Mac', 'Mohan', 'M', 'M', 'M')"
try:
    # 执行sql语句
    cursor.execute(sql)
    # 执行sql语句
    db.commit()
    print("insert ok")
except:
    # 发生错误时回滚
    db.rollback()
# 关闭数据库连接
db.close()

爬取视频

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import re
import requests
from bs4 import BeautifulSoup


def download(url):
    dz = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}
    req = requests.get(url,headers = dz).content
    with open('qq.mp4', 'wb') as fp:
        fp.write(req)





download('http://video.study.163.com/edu-video/nos/mp4/2017/04/01/1006064693_cc2842f7dc8b410c96018ec618f37ef6_sd.mp4?ak=d2e3a054a6a144f3d98805f49b4f04439064ce920ba6837d89a32d0b0294ad3c1729b01fa6a0b5a3442ba46f5001b48b1ee2fb6240fc719e1b3940ed872a11f180acad2d0d7744336d03591c3586614af455d97e99102a49b825836de913910ef0837682774232610f0d4e39d8436cb9a153bdeea4a2bfbae357803dfb6768a742fe395e87eba0c3e30b7b64ef1be06585111bf60ea26d5dad1f891edd9e94a8e167e0b04144490499ffe31e0d97a0a1babcbd7d2e007d850cc3bf7aa697e8ff')

爬取音频

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import json
import requests
from bs4 import BeautifulSoup


def download(url):
    hd = {
        'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"}

    req = requests.get(url, headers=hd)
    reps = req.text
    result = json.loads(reps)
    datap = result['data']['tracksAudioPlay']
    for index in datap:
        title = index['trackName']
        index['src']
        print(index['src'])
        data = requests.get(index['src'], headers=hd).content
        try:
            with open('%s.mp3' % title, 'wb') as f:
                f.write(data)
        except BaseException:
            print('1')


download('http://www.ximalaya.com/revision/play/album?albumId=7371372&pageNum=1&sort=-1&pageSize=30')

爬取文字

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import requests

from bs4 import BeautifulSoup

def get_h(url):
    response = requests.get(url)
    response .encoding = 'utf-8'
    return response.text

def get_c(html):
    soup = BeautifulSoup(html,'html.parser')
    joke_content = soup.select('div.content')[0].getText
    return joke_content
url_joke = "https://www.qiushibaike.com"
html = get_h(url_joke)
joke_content = get_c(html)
print(joke_content)

爬取图片

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import requests
from bs4 import BeautifulSoup
import os

headers = {
    'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
url = 'http://www.ivsky.com/'
start_html = requests.get(url, headers=headers)
Soup = BeautifulSoup(start_html.text, 'html.parser')
all_div = Soup.find_all('div', class_='syl_pic')
for lsd in all_div:
    lsds = 'http://www.ivsky.com' + lsd.find('a')['href']
    title = lsd.find('a').get_text
    print(lsds)
    html = requests.get(lsds, headers=headers)
    Soup_new = BeautifulSoup(html.text, 'html.parser')
    app = Soup_new.find_all('div', class_='il_img')
    for app_new in app:
        apptwo = 'http://www.ivsky.com' + app_new.find('a')['href']
        htmlthree = requests.get(apptwo, headers=headers)
        Soupthree = BeautifulSoup(htmlthree.text, 'html.parser')
        appthree = Soupthree.find('div', class_='pic')
        appf = appthree.find('img')['src']
        name = appf[-9:-4]
        img = requests.get(appf, headers=headers)
        f = open(name + '.jpg', 'ab')  ##写入多媒体文件必须要 b 这个参数！！必须要！！
        f.write(img.content)  ##多媒体文件要是用conctent哦！
        f.close()

爬取小说

#!/usr/bin/python
# -*- coding: UTF-8 -*-

from urllib import request
from bs4 import BeautifulSoup
import re
import sys

if __name__ == "__main__":
    #创建txt文件
    file = open('一念永恒.txt', 'w', encoding='utf-8')
    #一念永恒小说目录地址
    target_url = 'http://www.biqukan.com/1_1094/'
    #User-Agent
    head = {}
    head['User-Agent'] = 'Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166  Safari/535.19'
    target_req = request.Request(url = target_url, headers = head)
    target_response = request.urlopen(target_req)
    target_html = target_response.read().decode('gbk','ignore')
    #创建BeautifulSoup对象
    listmain_soup = BeautifulSoup(target_html,'html.parser')
    #搜索文档树,找出div标签中class为listmain的所有子标签
    chapters = listmain_soup.find_all('div',class_ = 'listmain')
    #使用查询结果再创建一个BeautifulSoup对象,对其继续进行解析
    download_soup = BeautifulSoup(str(chapters), 'html.parser')
    #计算章节个数
    numbers = (len(download_soup.dl.contents) - 1) / 2 - 8
    index = 1
    #开始记录内容标志位,只要正文卷下面的链接,最新章节列表链接剔除
    begin_flag = False
    #遍历dl标签下所有子节点
    for child in download_soup.dl.children:
        #滤除回车
        if child != '\n':
            #找到《一念永恒》正文卷,使能标志位
            if child.string == u"《一念永恒》正文卷":
                begin_flag = True
            #爬取链接并下载链接内容
            if begin_flag == True and child.a != None:
                download_url = "http://www.biqukan.com" + child.a.get('href')
                download_req = request.Request(url = download_url, headers = head)
                download_response = request.urlopen(download_req)
                download_html = download_response.read().decode('gbk','ignore')
                download_name = child.string
                soup_texts = BeautifulSoup(download_html, 'html.parser')
                texts = soup_texts.find_all(id = 'content', class_ = 'showtxt')
                soup_text = BeautifulSoup(str(texts), 'html.parser')
                write_flag = True
                file.write(download_name + '\n\n')
                #将爬取内容写入文件
                for each in soup_text.div.text.replace('\xa0',''):
                    if each == 'h':
                        write_flag = False
                    if write_flag == True and each != ' ':
                        file.write(each)
                    if write_flag == True and each == '\r':
                        file.write('\n')
                file.write('\n\n')
                #打印爬取进度
                sys.stdout.write("已下载:%.3f%%" % float(index/numbers) + '\r')
                sys.stdout.flush()
                index += 1
    file.close()