用python写网络爬虫学习笔记（一）

1. 写爬虫一般用的都是python，pip是python很重要的管理工具，相当于npm置于javascript吧。

在Mac上安装pip：

sudo easy_install pip

2. builtwith模块：用于检查网站构建的技术类型。

pip install builtwith

3. python-whois查询网站所有者

pip install python-whois

4. 第一个爬虫脚本

import urllib2
def download(url):
    print 'Downloading:', url
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
    return html

download("http://mp.blog.csdn.net/postedit?ref=toolbar")

使用urllib2模块下载URL。

4.1 根据返回的不同错误进行处理，以增强程序健壮性

404：无需重新下载，因为页面不存在即使重新下载也不会存在。

4xx：发生在请求存在问题时

5xx：发生在服务端存在问题时

对5xx错误通过递归进行重试。

import urllib2
def download(url, num_retries=2):
    print 'Downloading:', url
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
        if num_retries >0:
            if hasattr(e, 'code') and 500<= e.code < 600:
                # recursively retry 5xx HTTP errors
                return download(url, num_retries-1)
    return html

download("http://mp.blog.csdn.net/postedit?ref=toolbar")

4.2 设置用户代理：

import urllib2
def download(url, user_agent='wswp' ,num_retries=2):
    print 'Downloading:', url
    headers = {'User-agent': user_agent}
    request = urllib2.Request(url, headers=headers)
    try:
        html = urllib2.urlopen(request).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
        if num_retries >0:
            if hasattr(e, 'code') and 500<= e.code < 600:
                # recursively retry 5xx HTTP errors
                return download(url, num_retries-1)
    return html

download("http://mp.blog.csdn.net/postedit?ref=toolbar")

4.3 根据id爬数据

import itertools
import urllib2
def download(url):
    print 'Downloading:', url
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
    return html
for page in itertools.count(1):
    url = 'http://example.webscraping.com/view/-%d' % page
    html = download(url)
    if html is None:
        break
    else:
        pass

增强健壮性：

import itertools
import urllib2
def download(url):
    print 'Downloading:', url
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
    return html

max_errors = 5
num_errors = 0
for page in itertools.count(1):
    url = 'http://example.webscraping.com/view/-%d' % page
    html = download(url)
    if html is None:
        num_errors += 1
        if num_errors == max_errors:
            break
    else:
        num_errors = 0

4.4 链接爬虫：使用正则表达式来确定需要下载哪些页面。

import re
import urllib2
import urlparse
def download(url):
    print 'Downloading:', url
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError as e:
        print 'Download error:', e.reason
        html = None
    return html

def link_crawler(seed_url, link_regex):
    """Crawl from the given seed URL following links matched by link_regex"""
    crawl_queue = [seed_url]
    seen = set(crawl_queue)
    while crawl_queue:
        url = crawl_queue.pop()
        html = download(url)
        for link in get_links(html):
            if re.match(link_regex, link):
                link = urlparse.urljoin(seed_url, link)
                if link not in seen:
                    seen.add(link)
                    crawl_queue.append(link)

def get_links(html):
    """Return a list of links from html"""
    webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']',re.IGNORECASE)
    return webpage_regex.findall(html)


link_crawler('http://example.webscraping.com','/(index|view)')

5. robotparser：解析robot.txt文件

import robotparser

rp = robotparser.RobotFileParser()
rp.set_url('http://example.webscraping.com/robots.txt')
rp.read()
url = 'http://example.webscraping.com'
user_agent = 'BadCrawler'
rp.can_fetch(user_agent, url)

6. 下载限速：通过添加延时，对爬虫限速。

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()

7. 避免爬虫陷阱

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)

8. 完整爬虫

import re
import urlparse
import urllib2
import time
from datetime import datetime
import 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, num_retries, data=None):
    print 'Downloading:', url
    request = urllib2.Request(url, data, headers)
    opener = urllib2.build_opener()
    if proxy:
        proxy_params = {urlparse.urlparse(url).scheme: proxy}
        opener.add_handler(urllib2.ProxyHandler(proxy_params))
    try:
        response = opener.open(request)
        html = response.read()
        code = response.code
    except urllib2.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(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='GoodCrawler')