Python 2.7.6 爬虫实例

  • Z时代
  • 2024-01-10
  • 分类：综合

python

环境

Ubuntu 14.04 LTS

Python 2.7.6

Beautifulsoup4-4.6.0

PyCharm Community Edition 2017.1.2

 

PS：之前使用Python3配合Beautifulsoup老是有问题，改成Python2.7版本就好了。注意版本的搭配。

 

 

一 安装BeautifulSoup

BeautifulSoup官网：https://www.crummy.com/software/BeautifulSoup/

 

各版本：https://www.crummy.com/software/BeautifulSoup/bs4/download/

 

 

运行：$sudo pip install beautifulsoup4　进行安装

zh@zh:~$pip install beautifulsoup4
Downloading/unpacking beautifulsoup4
  Downloading beautifulsoup4-4.6.0-py2-none-any.whl (86kB): 86kB downloaded
Installing collected packages: beautifulsoup4
Cleaning up...
Exception:
Traceback (most recent call last):
  File "/usr/lib/python2.7/dist-packages/pip/basecommand.py", line 122, in main
    status = self.run(options, args)
  File "/usr/lib/python2.7/dist-packages/pip/commands/install.py", line 283, in run
    requirement_set.install(install_options, global_options, root=options.root_path)
  File "/usr/lib/python2.7/dist-packages/pip/req.py", line 1436, in install
    requirement.install(install_options, global_options, *args, **kwargs)
  File "/usr/lib/python2.7/dist-packages/pip/req.py", line 672, in install
    self.move_wheel_files(self.source_dir, root=root)
  File "/usr/lib/python2.7/dist-packages/pip/req.py", line 902, in move_wheel_files
    pycompile=self.pycompile,
  File "/usr/lib/python2.7/dist-packages/pip/wheel.py", line 206, in move_wheel_files
    clobber(source, lib_dir, True)
  File "/usr/lib/python2.7/dist-packages/pip/wheel.py", line 193, in clobber
    os.makedirs(destsubdir)
  File "/usr/lib/python2.7/os.py", line 157, in makedirs
    mkdir(name, mode)
OSError: [Errno 13] Permission denied: \'/usr/local/lib/python2.7/dist-packages/bs4\'
Storing debug log for failure in /home/zhanghu/.pip/pip.log
zh@zh:~$
zh@zh:~$
zh@zh:~$sudo pip install beautifulsoup4
[sudo] password for zhanghu: 
Downloading/unpacking beautifulsoup4
  Downloading beautifulsoup4-4.6.0-py2-none-any.whl (86kB): 86kB downloaded
Installing collected packages: beautifulsoup4
Successfully installed beautifulsoup4
Cleaning up...
zh@zh:~$

 

 

 

二　爬虫脚本案例1

# coding: utf-8
import urllib2
from bs4 import BeautifulSoup
class Splider:
    def __init__(self):
        self.manager = Manager()
        self.downloader = Download()
        self.parser = Parse()
        self.outputer = Output()
    def craw_search_word(self, root_url):
        count = 0
        self.manager.add_new_url(root_url)
        while self.manager.has_new_url():
            try:
                if count >= 10000:
                    break
                print "正在加载第" + str(count) + "到" + str(count + 15) + "条数据"
                current_url = self.manager.get_new_url()
                html_content = self.downloader.download(current_url)
                new_url, data = self.parser.parse(root_url, html_content)
                self.manager.add_new_url(new_url)
                # self.outputer.collect(data)
                self.outputer.output(data)
                count += 15
            except urllib2.URLError, e:
                if hasattr(e, "reason"):
                    print "craw faild, reason: " + e.reason
class Manager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    def add_new_url(self, new_url):
        if new_url is None:
            return None
        elif new_url not in self.new_urls and new_url not in self.old_urls:
            self.new_urls.add(new_url)
    def has_new_url(self):
        return len(self.new_urls) != 0
    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url
class Download(object):
    def download(self, url):
        if url is None:
            return None
        headers = {
                   "User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:52.0) Gecko/20100101 Firefox/52.0",
                   "Cookie" : "Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1466075280; __utma=194070582.826403744.1466075281.1466075281.1466075281.1; __utmv=194070582.|2=User%20Type=Visitor=1; signin_redirect=http%3A%2F%2Fwww.jianshu.com%2Fsearch%3Fq%3D%25E7%2594%259F%25E6%25B4%25BB%26page%3D1%26type%3Dnote; _session_id=ajBLb3h5SDArK05NdDY2V0xyUTNpQ1ZCZjNOdEhvNUNicmY0b0NtMnVuUUdkRno2emEyaFNTT3pKWTVkb3ZKT1dvbTU2c3c0VGlGS0wvUExrVW1wbkg1cDZSUTFMVVprbTJ2aXhTcTdHN2lEdnhMRUNkM1FuaW1vdFpNTDFsQXgwQlNjUnVRczhPd2FQM2sveGJCbDVpQUVWN1ZPYW1paUpVakhDbFVPbEVNRWZzUXh5R1d0LzE2RkRnc0lJSHJEOWtnaVM1ZE1yMkt5VC90K2tkeGJQMlVOQnB1Rmx2TFpxamtDQnlSakxrS1lxS0hONXZnZEx0bDR5c2w4Mm5lMitESTBidWE4NTBGNldiZXVQSjhjTGNCeGFOUlpESk9lMlJUTDVibjNBUHdDeVEzMGNaRGlwYkg5bHhNeUxJUVF2N3hYb3p5QzVNTDB4dU4zODljdExnPT0tLU81TTZybUc3MC9BZkltRDBiTEsvU2c9PQ%3D%3D--096a8e4707e00b06b996e8722a58e25aa5117ee9; CNZZDATA1258679142=1544596149-1486533130-https%253A%252F%252Fwww.baidu.com%252F%7C1486561790; _ga=GA1.2.826403744.1466075281; _gat=1",
                   "Accept" : "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
                   }
        content = ""
        try:
            request = urllib2.Request(url, headers = headers)
            response = urllib2.urlopen(request)
            content = response.read()
        except urllib2.URLError, e:
            if hasattr(e, "reason") and hasattr(e, "code"):
                print e.code
                print e.reason
            else:
                print "请求失败"
        return content
class Parse(object):
    def get_new_data(self, root_url, ul):
        data = set()
        lis = ul.find_all("li", {"class" : "have-img"})
        for li in lis:
            cont = li.find("div", {"class" : "content"})
            title = cont.find("a", {"class" : "title"}).get_text()
            title_url = root_url + cont.a["href"]
            data.add((title, title_url))
        return data
    def get_new_url(self, root_url, ul):
        lis = ul.find_all("li", {"class" : "have-img"})
        data_category_id = ul["data-category-id"]
        # 最后一个文章data-recommended-at －1
        max_id = int(lis[-1]["data-recommended-at"]) - 1
        new_url = root_url + "?data_category_id=" + data_category_id + "&max_id=" + str(max_id)
        return new_url
    def parse(self, root_url, content):
        soup = BeautifulSoup(content, "html.parser", from_encoding="utf-8")
        div = soup.find(id="list-container")
        ul = div.find("ul", {"class" : "note-list"})
        new_url = self.get_new_url(root_url, ul)
        new_data = self.get_new_data(root_url, ul)
        return new_url, new_data
class Output(object):
    def __init__(self):
        self.datas = set()
    def collect(self, data):
        if data is None:
            return None
        for item in data:
            if item is None or item in self.datas:
                continue
            self.datas.add(item)
    def output(self, data):
        for item in data:
            title, url = item
            print title + "                       " + url
if __name__ == "__main__":
    root_url = "http://www.jianshu.com/recommendations/notes"
    splider = Splider()
    splider.craw_search_word(root_url)

参考：http://www.jianshu.com/p/ffc221e3e404

 

二　爬虫脚本案例2

功能：抓取贴吧的图片

#coding=utf-8
import urllib
import re
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
def getImg(html):
    reg = r\'src="(.+?\.jpg)" pic_ext\'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,\'%s.jpg\' % x)
        x+=1
html = getHtml("https://tieba.baidu.com/p/2460150866")
print getImg(html)

 

上面脚本运行结束后，图片已经下载下来了：

参考：http://www.cnblogs.com/fnng/p/3576154.html

 

类似上面脚本，修改地址和正则表达式，下载"简书"的长微博图片：{这个脚本很不错}

如网址：http://www.jianshu.com/p/ffc221e3e404

1.把整个网页打印出来：

#coding=utf-8
import urllib
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
html = getHtml("http://www.jianshu.com/p/ffc221e3e404")
print html

 

将上面终端的数据拷贝到文本里面，或通过火狐浏览器右键"查看页面源代码"，然后搜索关键字"jpg"，找到图片的下载地址，如：

          <a class="share-circle" data-toggle="tooltip" href="http://cwb.assets.jianshu.io/notes/images/8978350/weibo/image_796105d290f5.jpg" target="_blank" data-original-title="下载长微博图片">

修改上面脚本中的正则表达式：

reg = r\'src="(.+?\.jpg)" pic_ext\'

修改为：

reg = r\'href="(.+?\.jpg)" target\'

然后运行脚本，完整脚本：

#coding=utf-8
import urllib
import re
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
def getImg(html):
    reg = r\'href="(.+?\.jpg)" target\'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,\'%s.jpg\' % x)
        x+=1
html = getHtml("http://www.jianshu.com/p/ffc221e3e404")
print getImg(html)

 

"长微博图片"已经下载下来了：

 

修改上面的URI和正则表达式就可以抓取网页上你想要的内容了。正则表达式如何写，完全要根据实际页面来匹配，而不是通用的。

 

2.筛选页面数据

通过"正则表达式"筛选

 

 

 

附：

抓取"http://www.3lian.com/gif/2017/05-12/669d0db509ee5c5a8f4a607f64b8e8c1.html" 界面的图片脚本：

#coding=utf-8
import urllib
import re
def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html
def getImg(html):
    reg = r\'src="(.+?\.jpg)"\'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,\'%s.jpg\' % x)
        x+=1
html = getHtml("http://www.3lian.com/gif/2017/05-12/669d0db509ee5c5a8f4a607f64b8e8c1.html")
print getImg(html)

 

 

http://blog.csdn.net/lishk314/article/details/44678019#    python下载音乐文件

 

三　爬虫脚本案例３

功能：下载视频网站的视频 

import urllib2
print "stand"
for i in range(1, 23, 1):
    url = \'http://newoss.maiziedu.com/yxyh4/pand-%02d.mp4\' % i
    f = urllib2.urlopen(url)
    data = f.read()
    name = \'python_pandas_%02d.mp4\' % (i)
    with open(name, "wb") as code:
        code.write(data)
print \'end\'

 

下载结果：

参考：

http://blog.csdn.net/hpuhjl/article/details/56012081　　　 Python - 下载视频网站的视频

 

另附

http://blog.csdn.net/hpuhjl/article/details/52253698　　　 python - 文件下载

http://www.cnblogs.com/yinsolence/p/5140297.html?utm_source=tuicool&utm_medium=referral  python爬取并下载麦子学院所有视频教程

http://git.oschina.net/getsai/mzSpider/tree/master   python爬取并下载麦子学院所有视频教程

 

http://blog.csdn.net/jiangwei0910410003/article/details/19806999   fidder抓包调试

以上是 Python 2.7.6 爬虫实例 的全部内容， 来源链接： utcz.com/z/386609.html

回到顶部