Python爬虫入门【21】： 知乎网全站用户爬虫 scrapy

class ZhihuSpider(scrapy.Spider):
    name = 'Zhihu'
    allowed_domains = ['www.zhihu.com']
    start_urls = ['https://www.zhihu.com/people/zhang-jia-wei/following']

    def parse(self, response):
        all_data = response.body_as_unicode()
        print(all_data)

from zhihu.settings import USER_AGENT_LIST # 导入中间件
import random

class RandomUserAgentMiddleware(object):
    def process_request(self, request, spider):
        rand_use  = random.choice(USER_AGENT_LIST)
        if rand_use:
            request.headers.setdefault('User-Agent', rand_use)
Python资源分享qun 784758214 ,内有安装包，PDF，学习视频，这里是Python学习者的聚集地，零基础，进阶，都欢迎

BOT_NAME = 'zhihu'

SPIDER_MODULES = ['zhihu.spiders']
NEWSPIDER_MODULE = 'zhihu.spiders'
USER_AGENT_LIST=[  # 可以写多个，测试用，写了一个
    "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"
]
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 2
# Disable cookies (enabled by default)
COOKIES_ENABLED = False
# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  'Accept-Language': 'en',
}
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    'zhihu.middlewares.RandomUserAgentMiddleware': 400,
}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'zhihu.pipelines.ZhihuPipeline': 300,
}

 # 起始位置
    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(url.format("zhang-jia-wei"), callback=self.parse)

    def parse(self, response):

        print("正在获取 {} 信息".format(response.url))
        all_data = response.body_as_unicode()

        select = Selector(response)

        # 所有知乎用户都具备的信息
        username = select.xpath("//span[@class='ProfileHeader-name']/text()").extract_first()       # 获取用户昵称
        sex = select.xpath("//div[@class='ProfileHeader-iconWrapper']/svg/@class").extract()
        if len(sex) > 0:
            sex = 1 if str(sex[0]).find("male") else 0
        else:
            sex = -1
        answers = select.xpath("//li[@aria-controls='Profile-answers']/a/span/text()").extract_first()
        asks = select.xpath("//li[@aria-controls='Profile-asks']/a/span/text()").extract_first()
        posts = select.xpath("//li[@aria-controls='Profile-posts']/a/span/text()").extract_first()
        columns = select.xpath("//li[@aria-controls='Profile-columns']/a/span/text()").extract_first()
        pins = select.xpath("//li[@aria-controls='Profile-pins']/a/span/text()").extract_first()
        # 用户有可能设置了隐私，必须登录之后看到，或者记录cookie！
        follwers = select.xpath("//strong[@class='NumberBoard-itemValue']/@title").extract()

        item = ZhihuItem()
        item["username"] = username
        item["sex"] = sex
        item["answers"] = answers
        item["asks"] = asks
        item["posts"] = posts
        item["columns"] = columns
        item["pins"] = pins
        item["follwering"] = follwers[0] if len(follwers) > 0 else 0
        item["follwers"] = follwers[1] if len(follwers) > 0 else 0

        yield item

        # 获取第一页关注者列表
        pattern = re.compile('<script id=\"js-initialData\" type=\"text/json\">(.*?)<\/script>')
        json_data = pattern.search(all_data).group(1)
        if json_data:
            users = json.loads(json_data)["initialState"]["entities"]["users"]
        for user in users:
            yield scrapy.Request(self.start_urls[0].format(user),callback=self.parse, dont_filter=False)
Python资源分享qun 784758214 ,内有安装包，PDF，学习视频，这里是Python学习者的聚集地，零基础，进阶，都欢迎