Python获取网页资源
前言
提示:以下是本篇文章正文内容,下面案例可供参考
一、Python爬取高清桌面壁纸
1.UserAgent.py源码
代码如下(示例):
import random
user_agent = [
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
# iPhone 6
"Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
# 新版移动ua
"Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"
]
# 随机获取一个请求头
def get_headers():
return {'User-Agent': random.choice(user_agent)}
2.netbian-1920-1080.py源码
代码如下(示例):
import requests
from bs4 import BeautifulSoup
import os
import time
import random
import UserAgent
index = 'http://www.netbian.com' # 网站根地址
interval = 0.1 # 爬取图片的间隔时间
firstDir = r'E:\py\python3.7\test\test35' # 总路径
classificationDict = {} # 存放网站分类子页面的信息
# 获取页面筛选后的内容列表
def screen(url, select):
headers = UserAgent.get_headers() # 随机获取一个headers
html = requests.get(url = url, headers = headers)
html.encoding = 'gbk' # 网站的编码
html = html.text
soup = BeautifulSoup(html, 'lxml')
return soup.select(select)
# 获取页码
def screenPage(url, select):
html = requests.get(url = url, headers = UserAgent.get_headers())
html.encoding = 'gbk'
html = html.text
soup = BeautifulSoup(html, 'lxml')
return soup.select(select)[0].next_sibling.text
# 下载操作
def download(src, name, path):
if(isinstance(src, str)):
response = requests.get(src)
path = path + '/' + name + '.jpg'
while(os.path.exists(path)): # 若文件名重复
path = path.split(".")[0] + str(random.randint(2, 17)) + '.' + path.split(".")[1]
with open(path,'wb') as pic:
for chunk in response.iter_content(128):
pic.write(chunk)
# 定位到 1920 1080 分辨率图片
def handleImgs(links, path):
for link in links:
href = link.get('href')
if(href == 'http://pic.netbian.com/'): # 过滤图片广告
continue
# 第一次跳转
if('http://' in href): # 有极个别图片不提供正确的相对地址
url = href
else:
url = index + href
select = 'div#main div.endpage div.pic div.pic-down a'
link = screen(url, select)
if(link == []):
print(url + ' 无此图片,爬取失败')
continue
href = link[0].get('href')
# 第二次跳转
url = index + href
# 获取到图片了
select = 'div#main table a img'
link = screen(url, select)
if(link == []):
print(url + " 该图片需要登录才能爬取,爬取失败")
continue
name = link[0].get('alt').replace('\t', '').replace('|', '').replace(':', '').replace('\\', '').replace('/', '').replace('*', '').replace('?', '').replace('"', '').replace('<', '').replace('>', '')
print(name) # 输出下载图片的文件名
src = link[0].get('src')
if(requests.get(src).status_code == 404):
print(url + ' 该图片下载链接404,爬取失败')
print()
continue
print()
download(src, name, path)
time.sleep(interval)
# 选择下载分类子页面
def select_classification(choice):
print('---------------------------')
print('--------------' + choice + '-------------')
print('---------------------------')
secondUrl = classificationDict[choice]['url']
secondDir = classificationDict[choice]['path']
if(not os.path.exists(secondDir)):
os.mkdir(secondDir) # 创建分类目录
select = '#main > div.page > span.slh'
pageIndex = screenPage(secondUrl, select)
lastPagenum = int(pageIndex) # 获取最后一页的页码
for i in range(0, lastPagenum):
if i == 0:
url = secondUrl
else:
url = secondUrl + 'index_%d.htm' %(i+1)
print('--------------' + choice + ': ' + str(i+1) + '-------------')
path = secondDir + '/' + str(i+1)
if(not os.path.exists(path)):
os.mkdir(path) # 创建分类目录下页码目录
select = 'div#main div.list ul li a'
links = screen(url, select)
handleImgs(links, path)
# ui界面,用户选择下载分类
def ui():
print('--------------netbian-------------')
print('全部', end=' ')
for c in classificationDict.keys():
print(c, end=' ')
print()
choice = input('请输入分类名:')
if(choice == '全部'):
for c in classificationDict.keys():
select_classification(c)
elif(choice not in classificationDict.keys()):
print("输入错误,请重新输入!")
print('----')
ui()
else:
select_classification(choice)
# 将分类子页面信息存放在字典中
def init_classification():
url = index
select = '#header > div.head > ul > li:nth-child(1) > div > a'
classifications = screen(url, select)
for c in classifications:
href = c.get('href') # 获取的是相对地址
text = c.string # 获取分类名
if(text == '4k壁纸'): # 4k壁纸,因权限问题无法爬取,直接跳过
continue
secondDir = firstDir + '/' + text # 分类目录
url = index + href # 分类子页面url
global classificationDict
classificationDict[text] = {
'path': secondDir,
'url': url
}
def main():
if(not os.path.exists(firstDir)):
os.mkdir(firstDir) # 创建总目录
init_classification()
ui()
if __name__ == '__main__':
main()
二、Python爬取豆瓣电影清单
1.源码
代码如下(示例):
# -*- codeing = utf-8 -*-
from bs4 import BeautifulSoup # 网页解析,获取数据
import re # 正则表达式,进行文字匹配`
import urllib.request, urllib.error # 制定URL,获取网页数据
import xlwt # 进行excel操作
#import sqlite3 # 进行SQLite数据库操作
findLink = re.compile(r'<a href="(.*?)">') # 创建正则表达式对象,标售规则 影片详情链接的规则
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)
findTitle = re.compile(r'<span class="title">(.*)</span>')
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findJudge = re.compile(r'<span>(\d*)人评价</span>')
findInq = re.compile(r'<span class="inq">(.*)</span>')
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)
def main():
baseurl = "https://movie.douban.com/top250?start=" #要爬取的网页链接
# 1.爬取网页
datalist = getData(baseurl)
savepath = "豆瓣电影Top250.xls" #当前目录新建XLS,存储进去
# dbpath = "movie.db" #当前目录新建数据库,存储进去
# 3.保存数据
saveData(datalist,savepath) #2种存储方式可以只选择一种
# saveData2DB(datalist,dbpath)
# 爬取网页
def getData(baseurl):
datalist = [] #用来存储爬取的网页信息
for i in range(0, 10): # 调用获取页面信息的函数,10次
url = baseurl + str(i * 25)
html = askURL(url) # 保存获取到的网页源码
# 2.逐一解析数据
soup = BeautifulSoup(html, "html.parser")
for item in soup.find_all('div', class_="item"): # 查找符合要求的字符串
data = [] # 保存一部电影所有信息
item = str(item)
link = re.findall(findLink, item)[0] # 通过正则表达式查找
data.append(link)
imgSrc = re.findall(findImgSrc, item)[0]
data.append(imgSrc)
titles = re.findall(findTitle, item)
if (len(titles) == 2):
ctitle = titles[0]
data.append(ctitle)
otitle = titles[1].replace("/", "") #消除转义字符
data.append(otitle)
else:
data.append(titles[0])
data.append(' ')
rating = re.findall(findRating, item)[0]
data.append(rating)
judgeNum = re.findall(findJudge, item)[0]
data.append(judgeNum)
inq = re.findall(findInq, item)
if len(inq) != 0:
inq = inq[0].replace("。", "")
data.append(inq)
else:
data.append(" ")
bd = re.findall(findBd, item)[0]
bd = re.sub('<br(\s+)?/>(\s+)?', "", bd)
bd = re.sub('/', "", bd)
data.append(bd.strip())
datalist.append(data)
return datalist
# 得到指定一个URL的网页内容
def askURL(url):
head = { # 模拟浏览器头部信息,向豆瓣服务器发送消息
"User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122 Safari / 537.36"
}
# 用户代理,表示告诉豆瓣服务器,我们是什么类型的机器、浏览器(本质上是告诉浏览器,我们可以接收什么水平的文件内容)
request = urllib.request.Request(url, headers=head)
html = ""
try:
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
return html
# 保存数据到表格
def saveData(datalist,savepath):
print("save.......")
book = xlwt.Workbook(encoding="utf-8",style_compression=0) #创建workbook对象
sheet = book.add_sheet('豆瓣电影Top250', cell_overwrite_ok=True) #创建工作表
col = ("电影详情链接","图片链接","影片中文名","影片外国名","评分","评价数","概况","相关信息")
for i in range(0,8):
sheet.write(0,i,col[i]) #列名
for i in range(0,250):
# print("第%d条" %(i+1)) #输出语句,用来测试
data = datalist[i]
for j in range(0,8):
sheet.write(i+1,j,data[j]) #数据
book.save(savepath) #保存
# def saveData2DB(datalist,dbpath):
# init_db(dbpath)
# conn = sqlite3.connect(dbpath)
# cur = conn.cursor()
# for data in datalist:
# for index in range(len(data)):
# if index == 4 or index == 5:
# continue
# data[index] = '"'+data[index]+'"'
# sql = '''
# insert into movie250(
# info_link,pic_link,cname,ename,score,rated,instroduction,info)
# values (%s)'''%",".join(data)
# # print(sql) #输出查询语句,用来测试
# cur.execute(sql)
# conn.commit()
# cur.close
# conn.close()
# def init_db(dbpath):
# sql = '''
# create table movie250(
# id integer primary key autoincrement,
# info_link text,
# pic_link text,
# cname varchar,
# ename varchar ,
# score numeric,
# rated numeric,
# instroduction text,
# info text
# )
#
#
# ''' #创建数据表
# conn = sqlite3.connect(dbpath)
# cursor = conn.cursor()
# cursor.execute(sql)
# conn.commit()
# conn.close()
# 保存数据到数据库
if __name__ == "__main__": # 当程序执行时
# 调用函数
main()
# init_db("movietest.db")
print("爬取完毕!")
总结
以上,谢谢大家
仅适用于新手小白学习!