import re
import json
import datetime
try:
import urlparse as parse
except:
from urllib import parse
import scrapy
from scrapy.loader import ItemLoader
from items import ZhihuQuestionItem, ZhihuAnswerItem
class ZhihuSpider(scrapy.Spider):
name = "zhihu_sel"
allowed_domains = ["www.zhihu.com"]
start_urls = ['https://www.zhihu.com/']
start_answer_url = "https://www.zhihu.com/api/v4/questions/{0}/answers?sort_by=default&include=data%5B%2A%5D.is_normal%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccollapsed_counts%2Creviewing_comments_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Cmark_infos%2Ccreated_time%2Cupdated_time%2Crelationship.is_author%2Cvoting%2Cis_thanked%2Cis_nothelp%2Cupvoted_followees%3Bdata%5B%2A%5D.author.is_blocking%2Cis_blocked%2Cis_followed%2Cvoteup_count%2Cmessage_thread_token%2Cbadge%5B%3F%28type%3Dbest_answerer%29%5D.topics&limit={1}&offset={2}"
headers = {
"HOST": "www.zhihu.com",
"Referer": "https://www.zhizhu.com",
'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
}
custom_settings = {
"COOKIES_ENABLED": True
}
def parse(self, response):
pass
def parse_question(self, response):
pass
def parse_answer(self, reponse):
pass
def start_requests(self):
from selenium import webdriver
browser = webdriver.Chrome(executable_path="E:/tmp/chromedriver.exe")
browser.get("https://www.zhihu.com/signin")
browser.find_element_by_css_selector(".SignFlow-accountInput.Input-wrapper input").send_keys(
"xxx")
browser.find_element_by_css_selector(".SignFlow-password input").send_keys(
"xxx")
browser.find_element_by_css_selector(
".Button.SignFlow-submitButton").click()
import time
time.sleep(10)
Cookies = browser.get_cookies()
print(Cookies)
cookie_dict = {}
import pickle
for cookie in Cookies:
f = open('H:/scrapy/ArticleSpider/cookies/zhihu/' + cookie['name'] + '.zhihu', 'wb')
pickle.dump(cookie, f)
f.close()
cookie_dict[cookie['name']] = cookie['value']
browser.close()
return [scrapy.Request(url=self.start_urls[0], dont_filter=True, cookies=cookie_dict)]
