python网页爬虫开发之四-串行爬虫代码示例

实现功能：代理、限速、深度、反爬

import re

import queue

import urllib.parse

import urllib.robotparser

import time

from urllib import request

from datetime import datetime

 

def download(url, user_agent="wsap", num=2):

    print("Downloading:"+url)

    try:

        req = request.Request(url)

        req.add_header('user_agent', user_agent)

        html = request.urlopen(req).read()

    except Exception as e:

        print('Download error:')

        html = None

        if num > 0:

            if hasattr(e, "code") and 500 <= e.code < 600:

                return download(url, user_agent, num-1)

    return html

 

def link_crawler(seed_url, link_regex=None, delay=5, max_depth=-1, max_urls=-1, headers=None, user_agent='BadCrawler', proxy=None, num_retries=1):

    crawl_queue = queue.deque([seed_url])

    seen = {seed_url: 0}

    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()

        if rp.can_fetch(user_agent, url):

            throttle.wait(url)

            html = download(url)

            links = []

            depth = seen[url]

            if depth != max_depth:

                if link_regex:

                    links.extend(link for link in get_links(html) if re.match(link_regex, link))

                for link in links:

                    link = normalize(seed_url, link)

                    if link not in seen:

                        seen[link] = depth +1

                        if same_domain(seed_url, link):

                            crawl_queue.append(link)

            num_urls += 1

            if num_urls == max_urls:

                break

        else:

            print('Blocked by robots.txt:'+url)

 

class Throttle:

    def __init__(self, delay):

        self.delay = delay

        self.domains = {}

 

    def wait(self, url):

        domain = urllib.parse.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 normalize(seed_url,link):

    link, _ = urllib.parse.urldefrag(link)

    return urllib.parse.urljoin(seed_url, link)

 

def same_domain(url1, url2):

    return urllib.parse.urlparse(url1).netloc == urllib.parse.urlparse(url2).netloc

 

def get_robots(url):

    rp = urllib.robotparser.RobotFileParser()

    rp.set_url(urllib.parse.urljoin(url, '/robots.txt'))

    rp.read()

    return rp

 

def get_links(html):

    webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)

    html = html.decode('utf-8')

    return webpage_regex.findall(html)

 

if __name__ == '__main__':

    link_crawler('http://example.webscraping.com', '/places/default/view/', delay=0, num_retries=1, max_depth=1, user_agent='GoodCrawler')