Python爬虫学习日记二 抓取

Python爬虫学习日记二  
                                冰冠   2018年06月14日08:59:27
从网页中抽取数据,实现某些事情的做法成为抓取(scraping)

1、分析网页数据  
    通过各种web开发者工具可以进行分析
2、三种网页抓取方法    
    2.1正则表达式
        有关正则表达式的内容具体请看
    https://blog.csdn.net/ice_cap1995/article/details/80694675
    2.2Beautiful Soup
        Beautiful Soup是一个python模块，该模块可以解析网页  安装
            pip install beautifulsoup4
        Beautiful soup的使用
            （1）将已下载的html内容解析为soup文档（2）查找
            beautifulsoup 能够正确解析缺失的引号并闭合标签。

           

from day01_crawl import crawling
from bs4 import BeautifulSoup

url = 'http://example.webscraping.com/places/default/view/China-47'
html = crawling.download(url)
soup = BeautifulSoup(html,"lxml")
tr = soup.find(attrs={'id':'places_area__row'})
td = tr.find(attrs={'class':'w2p_fw'})
area = td.text
print(area)

    2.3Lxml

        Lxml是基于libxml2的python 的封装，该模块使用c语言编写，解析速度快于BeautifulSoup
        安装也更为复杂，安装说明请看官方文档：http://Lxml.de/installation.html
       

import lxml.html

broken_html = '<ul class=country><li>Area<li>Population</ul>'
tree = lxml.html.fromstring(broken_html)
fixed_html = lxml.html.tostring(tree, pretty_print=True)
print(fixed_html.decode('utf-8'))

         使用lxml的css选择器
       

import crawling

url = 'http://example.webscraping.com/places/default/view/China-47'
html = crawling.download(url)
tree = lxml.html.fromstring(html)
td=tree.cssselect('tr#places_area__row>td.w2p_fw')[0]
area = td.text_content()
print(area)

        附：css选择器 不支持的功能可以查看https://cssselect.readthedocs.io/en/latest/#id8
            选择多有标签 *
            选择<a>标签  a
            选择所有class="link"的元素 .link
            选择所有class="link"的<a>标签 a.link
            选择id="link"的<a>标签 a#link
            选择父元素为<a>标签的所有span标签 a > span
            选择<a>标签你恶不的所有<span>标签 a span
            选择title属性为"'home"的所有<a>标签 a[title=home]\
    2.4总结

    抓取方法             性能        使用难度         安装难度
    正则表达式           快             困难            简单(内置模块)
    BeautifulSoup       慢            简单             简单(纯Python)
    Lxml                      快            简单             相对困难

    通常情况下 lxml是最好的选择方式,该方法即快速又健壮

3、为链接爬虫添加抓取回调

    为了复用已经写好的部分爬虫代码爬取其他网站，需要添加一个回调函数，在此起名为callback，包含url和html两个参数，并且可以返回一个待爬取的url列表

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
""" @author [email protected]
    @function:
    @create 18-6-14 上午10:48"""
import re
import csv
import lxml.html

from day02_scraping.crawling import link_crawler


class ScrapeCallback:
    def __init__(self):
        self.fields = (
            'area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code',
            'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages',
            'neighbours')
        self.write_2_file('countries.csv',self.fields)

    def write_2_file(self,file_name,row):
        with open(file_name, 'w', newline='') as csvfile:
            self.writer = csv.writer(csvfile, delimiter=' ',
                                     quotechar='|', quoting=csv.QUOTE_MINIMAL)
            self.writer.writerow(row)

    #     对象作为函数被调用是会调用该方法即 ScrapeCallback(url,html)和ScrapeCallback.__cell__(url,html)是等价的
    def __call__(self, url, html):
        if re.search('/view/', url):
            print(html.decode('utf-8'))
            tree = lxml.html.fromstring(html)
            row = []
            for field in self.fields:
                row.append(tree.cssselect('table > tr#places_{0}__row > td.w2p_fw'.format(field))[
                               0].text_content())
            self.write_2_file('countries.csv',row)

if __name__ == '__main__':
    link_crawler('http://example.webscraping.com/places/default/view/Zimbabwe-252', '(.*?)/(index|view)', scrape_callback=ScrapeCallback())

 

附：能用的链接爬虫示例

https://github.com/ice1995/python_web_crawler-/tree/master/day02_scraping

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
""" @author [email protected]
    @function:
    @create 18-6-14 上午10:39"""''
import lxml.html
import re
import urllib.parse
import urllib.request
import time
import csv
from datetime import datetime
import urllib.robotparser
import queue

FIELDS = ('area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code',
          'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages',
          'neighbours')


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, scrape_callback=None):
    """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 = [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()
        depth = seen[url]
        # 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 = []
            if scrape_callback:
                links.extend(scrape_callback(url, html) or [])

            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):
        """Delay if have accessed this domain recently
        """
        domain = urllib.parse.urlsplit(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 = urllib.request.Request(url, data, headers)
    opener = urllib.request.build_opener()
    if proxy:
        proxy_params = {urllib.parse.urllib.parse(url).scheme: proxy}
        opener.add_handler(urllib.request.ProxyHandler(proxy_params))
    try:
        response = opener.open(request)
        html = response.read()
        code = response.code
    except urllib.request.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
                html = 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, _ = urllib.parse.urldefrag(link)  # remove hash to avoid duplicates
    return urllib.parse.urljoin(seed_url, link)


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


def get_robots(url):
    """Initialize robots parser for this domain
    """
    rp = urllib.robotparser.RobotFileParser()
    rp.set_url(urllib.parse.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.decode('utf-8'))


def scrape_callback(url, html):
    if re.search('/view/', url):
        tree = lxml.html.fromstring(html)
        row = [tree.cssselect('table > tr#places_%s__row > td.w2p_fw' % field)[0].text_content()
               for field in FIELDS]
        print(url, row)


class ScrapeCallback:
    def __init__(self):
        self.fields = (
            'area', 'population', 'iso', 'country', 'capital', 'continent', 'tld', 'currency_code',
            'currency_name', 'phone', 'postal_code_format', 'postal_code_regex', 'languages',
            'neighbours')
        self.write_2_file('countries.csv', self.fields)

    def write_2_file(self, file_name, row):
        with open(file_name, 'a+') as csvfile:
            self.writer = csv.writer(csvfile, delimiter=' ',
                                     quotechar='|', quoting=csv.QUOTE_MINIMAL)
            self.writer.writerow(row)

    #     对象作为函数被调用是会调用该方法即 ScrapeCallback(url,html)和ScrapeCallback.__cell__(url,html)是等价的
    def __call__(self, url, html):
        if re.search('/view/', url):
            tree = lxml.html.fromstring(html)
            row = []
            for field in self.fields:
                list = tree.cssselect('table > tr#places_{0}__row > td.w2p_fw'.format(field))
                if len(list) > 0:
                    row.append(list[0].text_content())
            self.write_2_file('countries.csv', row)


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')
    # link_crawler('http://example.webscraping.com/', '/(index|view)',scrape_callback=scrape_callback)
    link_crawler('http://example.webscraping.com/', '(.*?)/(index|view)',
                 scrape_callback=ScrapeCallback())