import csv
import requests
from bs4 import BeautifulSoup
from itertools import izip
grant_number = ['0901289','0901282','0901260']
#IMPORTANT NOTE: PLACE GRANT NUMBERS BETWEEN STRINGS WITH NO SPACES
start = 'this site'
end = 'Please report errors'
#start and end show the words that come right before the publication data
my_string = []
#my_string is an empty list for the publication data
for x in grant_number: # Number of pages plus one
url = "http://nsf.gov/awardsearch/showAward?AWD_ID={}".format(x)
r = requests.get(url)
soup = BeautifulSoup(r.content, "html.parser")
soup_string = str(soup)
my_string[int(x)] = soup_string[(soup_string.index(start)+len(start)):soup_string.index(end)]
with open('NSF.csv', 'wb') as f:
#Default Filename is NSF.csv ; This can be changed by editing the first field after 'open('
writer = csv.writer(f)
writer.writerows(izip(grant_number, my_string))
#this imports the lists into a csv file with two columns, grant number on left, publication data on right
Python 告诉我这一点
line 26, in my_string[int(x)] = soup_string[(soup_string.index(start)+len(start)):soup_string.index(end)] IndexError: list assignment index out of range
我该如何解决这个问题?
最佳答案
问题是 my_string[x]
正在尝试获取 my_string 的 x 列表索引,但根据您对 grant_number 列表的定义,x 是一个字符串。
您可能想附加到最初的空字符串。
for x in grant_number: # Number of pages plus one
url = "http://nsf.gov/awardsearch/showAward?AWD_ID={}".format(x)
r = requests.get(url)
soup = BeautifulSoup(r.content, "html.parser")
soup_string = str(soup)
my_string.append(soup_string[(soup_string.index(start)+len(start)):soup_string.index(end)])
关于Python:html scraper,用于从具有相同基本 url 的多个页面中提取某些单词之间的信息。这是我到目前为止所拥有的,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/37645988/