This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
from research.items import ResearchItem | |
class ResearchSpider(scrapy.Spider): | |
start_urls = [ | |
'https://research.fb.com/people/' | |
] | |
name = 'research' | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
class CrosswebItem(scrapy.Item): | |
name=scrapy.Field() | |
city=scrapy.Field() | |
topics=scrapy.Field() | |
file_urls=scrapy.Field() | |
files=scrapy.Field() | |
description=scrapy.Field() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
from pycon.items import PyconItem | |
class HumanSpider(scrapy.Spider): | |
start_urls = [ | |
'http://pyvideo.org/speakers.html' | |
] | |
name = 'pycon' | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
from human.items import HumanItem | |
class HumanSpider(scrapy.Spider): | |
start_urls = [ | |
'http://humantalks.com/talks/' | |
] | |
name = 'human' | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import pycurl | |
from io import BytesIO | |
import json | |
import requests | |
buffer = BytesIO() | |
with open('events_2016.csv', newline='') as csvfile: | |
spamreader = csv.reader(csvfile, delimiter=',', quotechar='"') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
class QuotesSpider(scrapy.Spider): | |
name = "books" | |
start_urls = [ | |
'http://books.toscrape.com/catalogue/category/books/romance_8/index.html', | |
] | |
def parse(self, response): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
from scrapy.item import Item,Field | |
class ExpertItem(scrapy.Item): | |
name=Field() | |
tangline=Field() | |
file_urls=Field() | |
files=Field() | |
city=Field() | |
gplus=Field() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
### START BOILERPLATE CODE | |
# Sample Python code for user authorization | |
import httplib2 | |
import os | |
import sys | |
import pprint |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from scrapy.spiders import CrawlSpider, Rule | |
from mobile.items import MobileItem | |
from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor | |
from scrapy.selector import Selector | |
class MySpider(CrawlSpider): | |
name = "mobile" | |
allowed_domains = ["mobiletechcon.de"] | |
start_urls = ["https://mobiletechcon.de/speakers-en/"] |