网络爬虫笔记

爬虫采用python3 windows平台上

chapter 网页抓取

1、背景调查

包含内容：
(1、检查robots.txt
大多数网站都会定义robots.txt文件，了解具体有哪些限制。主要方式，URL/robots.txt查看
(2、检查网站地图，sitemap
通过robots.txt中，提供的sitemap。不过一般网站没有提供，用处不大。
(3、估算网站大小
估算网站大小，经常通过搜索引擎搜索下目标网页，会显示查到的数量，能够得到大致网页数量。
(4、识别网站所用的技术
应用builtwith包，可以输出网站所用的技术和，然后我们根据网站所用的技术去分析网页。
import builtwith
builtwith.parse(‘https://www.cnblogs.com/ironstark/p/5303924.html’)
废话不多说，开始写爬虫了。

2、爬取网页的基本方法

直接上代码

import urllib.request as rq
import re
import itertools
import urllib.parse as urlparse
import urllib.robotparser 
def download(url, user_agent='wswp', proxy =None ,num_retries=2):
    print('Downloading:',url)
    headers = {'User-agent':user_agent}  #使用代理
    request = rq.Request(url,headers=headers)
    opener = rq.build_opener()   #使用绝对路径访问
    if proxy :   #使用支持的代理
        proxy_params = {rq.urlparse(url).scheme:proxy}
        opener.add_handler(rq.ProxyHandler(proxy_params))
    try:
        html = opener.open(request).read()
    except rq.URLError as e:
        print('Download error :' ,e.reason)
        html = None
        if num_retries >0: #当访问网页出现504等由于网页延迟等原因，重新下载，默认2次
            if hasattr(e,'code') and 500 <= e.code <600:
                html = download(url,user_agent,proxy,num_retries-1)
    return html

3、偏离爬虫

（1）ID遍历法
id遍历法适用于，id是数值且id之间相隔不远，有一定规律的网页。

#maxnum number of consecutive download errors allowed
max_error = 5
#current number of consecutive download error
n = 0 
num_error = 0 
for page in  itertools.count(1):
  url = 'http://example.webscraping.com/view/-%d' %page
  html = download(url)
  if html is None:
      num_error +=1
      if num_error == max_error:
          break
  else:
      num_error = 0
      n +=1
      if n>=5:
          break
      print('download success')

(2) 链接爬取
优点：通过链接爬虫可以更像用户登录一样，这样可以让网页爬虫更好的工作，可以爬一些不能连续的网页
确定：会下载一些我们不需要的网页

def link_crawler(seed_url,link_regex):
  crawl_queue = [seed_url]
  seen = set(crawl_queue) #去除重复下载
  while crawl_queue:
      url = crawl_queue.pop()
      html = download(url)
      for link in get_links(html):
          if re.match(like_regex,link):
              link = urlparse.urljoin(seed_url,link)
              if link not in seen:    
                  seen.add(link)
                  crawl_queue.append(link)
                  
def get_links(html):   #获取链接的url
  webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']')
  return webpage_regex.findall(html)

4、爬虫的高级功能

（1）解析robots.txt文件，避免下载禁止爬取的url，使用 import urllib.robotparser
可以在

def link_crawler(seed_url,link_regex):
  crawl_queue = [seed_url]
  seen = set(crawl_queue) #去除重复下载
  while crawl_queue:
      url = crawl_queue.pop()
      html = download(url)
      for link in get_links(html):
          if re.match(like_regex,link):
              link = urlparse.urljoin(seed_url,link)
              if link not in seen:    
                  seen.add(link)
                  crawl_queue.append(link)
                  
def get_links(html):   #获取链接的url
  webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']')
  return webpage_regex.findall(html)

（2）限定爬取深度，以免进入爬虫陷阱

5、整合代码

# -*- coding: utf-8 -*-
"""
Created on Sat May 25 20:09:01 2019

@author: Administrator
"""

import re
import urllib.request as rq
import urllib.parse as urlparse
import time
from datetime import datetime
import urllib.robotparser as robotparser
import  queue 


def link_crawler(seed_url, link_regex=None, delay=5, max_depth=-1, max_urls=-1, headers=None, user_agent='wswp', proxy=None, num_retries=1):
    """Crawl from the given seed URL following links matched by link_regex
    """
    # the queue of URL's that still need to be crawled
    crawl_queue = queue.deque([seed_url])
    # the URL's that have been seen and at what depth
    seen = {seed_url: 0}
    # track how many URL's have been downloaded
    num_urls = 0
    rp = get_robots(seed_url)
    throttle = Throttle(delay)
    headers = headers or {}
    if user_agent:
        headers['User-agent'] = user_agent

    while crawl_queue:
        url = crawl_queue.pop()
        # check url passes robots.txt restrictions
        if rp.can_fetch(user_agent, url):
            throttle.wait(url)
            html = download(url, headers, proxy=proxy, num_retries=num_retries)
            links = []

            depth = seen[url]
            if depth != max_depth:
                # can still crawl further
                if link_regex:
                    # filter for links matching our regular expression
                    links.extend(link for link in get_links(html) if re.match(link_regex, link))

                for link in links:
                    link = normalize(seed_url, link)
                    # check whether already crawled this link
                    if link not in seen:
                        seen[link] = depth + 1
                        # check link is within same domain
                        if same_domain(seed_url, link):
                            # success! add this new link to queue
                            crawl_queue.append(link)

            # check whether have reached downloaded maximum
            num_urls += 1
            if num_urls == max_urls:
                break
        else:
            print ('Blocked by robots.txt:', url)


class Throttle:
    """Throttle downloading by sleeping between requests to same domain
    """
    def __init__(self, delay):
        # amount of delay between downloads for each domain
        self.delay = delay
        # timestamp of when a domain was last accessed
        self.domains = {}
        
    def wait(self, url):
        domain = urlparse.urlparse(url).netloc
        last_accessed = self.domains.get(domain)

        if self.delay > 0 and last_accessed is not None:
            sleep_secs = self.delay - (datetime.now() - last_accessed).seconds
            if sleep_secs > 0:
                time.sleep(sleep_secs)
        self.domains[domain] = datetime.now()

def download(url, headers={}, proxy=None, num_retries=2, data=None):
    print ('Downloading:', url)
    request = rq.Request(url, data, headers)
    opener = rq.build_opener()
    if proxy:
        proxy_params = {urlparse.urlparse(url).scheme: proxy}
        opener.add_handler(rq.ProxyHandler(proxy_params))
    try:
        response = opener.open(request)
        html = response.read()
        code = response.code
    except rq.URLError as e:
        print ('Download error:', e.reason)
        html = ''
        if hasattr(e, 'code'):
            code = e.code
            if num_retries > 0 and 500 <= code < 600:
                # retry 5XX HTTP errors
                return download(url, headers, proxy, num_retries-1, data)
        else:
            code = None
    return html


def normalize(seed_url, link):
    """Normalize this URL by removing hash and adding domain
    """
    link, _ = urlparse.urldefrag(link) # remove hash to avoid duplicates
    return urlparse.urljoin(seed_url, link)


def same_domain(url1, url2):
    """Return True if both URL's belong to same domain
    """
    return urlparse.urlparse(url1).netloc == urlparse.urlparse(url2).netloc


def get_robots(url):
    """Initialize robots parser for this domain
    """
    rp = robotparser.RobotFileParser()
    rp.set_url(urlparse.urljoin(url, '/robots.txt'))
    rp.read()
    return rp
        

def get_links(html):
    """Return a list of links from html 
    """
    # a regular expression to extract all links from the webpage
    webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)
    # list of all links from the webpage
    return webpage_regex.findall(str(html))
   
if __name__ == '__main__':
    link_crawler('http://example.webscraping.com', '/(index|view)', delay=0, num_retries=1, user_agent='BadCrawler')
    link_crawler('http://example.webscraping.com', '/(index|view)', delay=0, num_retries=1, max_depth=1, user_agent='wswp')

chapter 2 数据的抓取

网页抓取了，那怎么抓取网页上的数据呢？抓取数据主要有三种方法，正则表达式、Beautiful Soup和lxml三种方法。

抓取方法	性能	使用难度	优点	缺点
正则表达式	快	困难	快，使用面广	难，程序脆弱
Beautiful Soup	慢	使用简单	慢
LXML	较快	较容易	使用相对简单，速度快	–

一、