Crawler——鏈接爬蟲

對數據的提取和收集也是數據分析中一大重點，所以，學習爬蟲是非常有用的。完成數據採集，對後面的數據分析做下基礎。

今天，要介紹的是來自《Web Scraping With Python》中的一個示例——鏈接爬蟲。對於此類進行了簡單的總結，便於相互學習。

#! /usr/bin/env python
# -*- coding:utf-8 -*-
import re
import urlparse
import urllib2
import time
from datetime import datetime
import robotparser
import Queue
# 鏈接爬蟲
'''
一個鏈接爬蟲需要考慮以下幾個問題：
1.下載網頁時，我們可能會遇到不可控制的錯誤，比如請求的網頁可能不存在。就要用到try和except語句，捕獲異常。
2.下載網頁時，我們也可能會遇上臨時性的錯誤，比如伺服器過載返回的503 Service Unavailable錯誤。就要多嘗試幾次下載。
3.一些網站可能會封殺預設的用戶代理，所以，我們應該重新設置一個用戶代理user_agent='wswp'。
4.下載網站鏈接時，應當考慮符合自己目標的鏈接，篩選出自己感謝的東西。通常用正則表達式來匹配這些鏈接。'<a[^>]+href=["\'](.*?)["\']'.
5.應當考慮網頁中的鏈接是什麼鏈接，如果是絕對鏈接就沒事，如果是相對鏈接就應該創建絕對鏈接。urlparse.urljoin()
6.爬取網頁的時候，經常會出現將要爬取的網頁中也有爬取過的鏈接，這樣會造成不斷迴圈。所以要建立一個URL管理器，管理爬取過的和未爬取的
7.所有爬蟲都應當遵守爬蟲協議（robots.txt），所以要引入robotparser模塊，以避免下載禁止爬取的URL
8.有時我們需要使用代理訪問某個網站。
9.如果我們爬取網站的速度過快，就會面臨被封禁或者伺服器過載的風險。所以應當在兩次下載之間添加延時。delay
10.有些網站中含有動態內容，如果爬取該網頁就會出現無限制的網頁，所以為了避免爬蟲陷阱，最好設置一個爬取深度(max_depth)——記錄到達當前網頁經過了多少鏈接。
'''
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
                    for link in get_links(html):
                        if re.match(link_regex, link):
                            links.extend(link)
                    # 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')