如何指定范围而不限于数字
问题描述:
这是获取餐馆评论的代码。我正在收集评论。如何指定范围而不限于数字
指定并导入范围。但有一个问题。每家商店都有不同数量的评论。很少有评论的商店应该很快去下一个商店。
我受到的范围太大。但它不能缩小范围。这是因为一些商店在这个范围内有评论。
我该如何有效地工作?
我看到了所有?(元素)搜索此代码。但我不知道我是否错误地应用了我的代码。
#python3
import sys
from bs4 import BeautifulSoup
import urllib.request
import requests
from urllib.parse import quote
import time
import os
import xlwt
import random
import re
FISRT_URL = "https://www.yelp.com/search?
find_desc=Korean+Food&find_loc=Seattle,+WA&start="
LAST_URL = "&cflt=korean"
def get_link(URL, doc_name):
global jisu_i
global num
global page
for jisu_i in range(1):
current_page_num = 20 + jisu_i*10
position = URL.index('t=')
URL_with_page_num = URL[: position+2] + str(current_page_num) \
+ URL[position+2 :]
print(URL_with_page_num)
importurl = URL_with_page_num
r = requests.get(importurl)
soup = BeautifulSoup(r.content.decode('euc-kr','replace'), "lxml")
time.sleep(random.randint(10, 15))
for title in soup.find_all('h3')[page+2:21]:
page = page + 1
title_link = title.select('a')
for jisu_m in range(130):
print(page)
last_URL = title_link[0]['href']
print(last_URL)
first_URL = "https://www.yelp.com"
global article_URL
article_URL = first_URL + last_URL
time.sleep(random.randint(15, 30))
jisuurl = article_URL
for k in range(99): #
jisu_page_num = 0 + k * 20 #
position = jisuurl.index('?')
URL_with_page_num = jisuurl[: position + 1] + str("start=") + str(jisu_page_num)
jisu_with_page_num = URL_with_page_num
print(jisu_with_page_num)
jisu_importurl = jisu_with_page_num
get_text(URL, jisu_importurl, doc_name)
time.sleep(random.randint(40,180))