crawler/nld.py at master · laiviet/crawler · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
# -*- coding: utf-8 -*-
"""

@author: Viet Lai
"""
import scrapy
import io
import os
import logging

from article import Article
from bs4 import BeautifulSoup
from scrapy import signals
from scrapy.crawler import CrawlerProcess


class NewsSpider(scrapy.Spider):
    """Summary

    Attributes:
        crawled_history (str): Description
        crawled_pages (list): Description
        link_directory (str): Description
        name (str): Description
    """

    name = "nld"
    crawled_history = "history/{}.txt".format(name)
    crawled_pages = []

    @classmethod
    def from_crawler(cls, crawler, *args, **kwargs):
        """Summary

        Args:
            crawler (TYPE): Description
            *args: Description
            **kwargs: Description

        Returns:
            TYPE: Description
        """
        spider = super(NewsSpider, cls).from_crawler(crawler, *args, **kwargs)
        crawler.signals.connect(spider.spider_closed,
                                signal=signals.spider_closed)
        return spider

    def start_requests(self):
        """Summary

        Yields:
            TYPE: Description
        """
        self.load_crawled_pages()

        # get all text file in folder Links
        files = [x for x in os.listdir(self.name) if x.endswith('.txt')]
        for file in files:
            file_name = os.path.join(self.name, file)
            # self.log(file_name)
            #
            # read all links in each text file
            with open(file_name) as f:
                links = f.readlines()
            links = [x.strip() for x in links]

            # crawl data for each link
            base = os.path.basename(file_name)
            category = os.path.splitext(base)[0]
            try:
                os.mkdir(os.path.join(self.name, category))
            except:
                pass
            for link in links:
                page = link.split("/")[-1]
                if page not in self.crawled_pages:
                    yield scrapy.Request(url=link, callback=self.parse)
                    # break

    def parse(self, response):
        """Summary

        Args:
            response (TYPE): Description
        """
        container = response.css("div.contentleft")[0]

        title = container.css("h1").extract_first().strip()
        title = BeautifulSoup(title, "lxml").text.strip()

        description = container.css("h2").extract_first().strip()
        description = BeautifulSoup(description, "lxml").text.strip()

        paragraphs = container.css("div.contentdetail p").extract()
        paragraphs = [BeautifulSoup(p, "lxml").text.strip() for p in paragraphs]
        paragraphs = [x for x in paragraphs if len(x) > 0]

        author = container.css("div.nguon-tin-detail").extract()[0]
        print(author)
        author = BeautifulSoup(author, "lxml").text.strip()

        time = container.css('p.ngayxuatban').extract_first()
        time = BeautifulSoup(time, 'lxml').text.strip()

        page = response.url.split("/")[-1]
        id = page.split('.')[0].split('-')[-1]
        category = response.url.split('/')[3]
        filename = '{}/{}/{}.json'.format(self.name, category, id)

        directory_path = os.path.join(self.name, category)
        if not os.path.exists(directory_path):
            os.makedirs(directory_path)

        a = Article()
        a.url = response.url
        a.author = author
        a.title = title
        a.paragraphs = paragraphs
        a.description = description
        a.time = time

        print('Save: ', filename)
        with io.open(filename, 'w', encoding='utf8') as f:
            f.write(a.json())

            self.log('Saved: {}'.format(filename), level=logging.DEBUG)

        # append history
        self.crawled_pages.append(response.url)

    def spider_closed(self, spider):
        """Summary

        Args:
            spider (TYPE): Description
        """
        self.log('Spider Closed')
        self.save_crawled_pages()

    def load_crawled_pages(self):
        """Summary
        """
        if os.path.exists(self.crawled_history):
            with open(self.crawled_history) as f:
                pages = f.readlines()
            self.crawled_pages = [x.strip() for x in pages]

    def save_crawled_pages(self):
        """Summary
        """
        with open(self.crawled_history, 'w+') as f:
            for page in self.crawled_pages:
                f.writelines(page + '\n')
        print('Save history', len(self.crawled_pages))


process = CrawlerProcess()
process.crawl(NewsSpider)
process.start()