我如何将这个web抓取(数据)的输出放入pandas数据帧?
下面的代码只显示一行数据,并且是垂直排列的。如何使数据帧看起来完全像打印(数据)-即水平?
另外,我是个新手,这可不是Python。请建议如何使其成为函数(?)?
我尝试了所有类型的append和concat函数,但是嵌套循环会使一切都陷入错误。请帮忙。
提前谢谢你。在from bs4 import BeautifulSoup as bs
import urllib.request
import re
import pandas as pd
Url1 = 'http://www5.statcan.gc.ca/cimt-cicm/topNCountryCommodities-marchandises?lang=eng&chapterId=27§ionId=0&refMonth='
Url2 = '&refYr='
Url3 = '&freq=6&countryId=999&usaState=0&provId=1&arrayId=9900000&commodityId=271111&commodityName=Natural+gas%2C+liquefied&topNDefault=10&tradeType=3'
regexQ = re.compile('Date1 Qty')
regexC = re.compile('Footnote')
regexV = re.compile('Date1 Val')
import csv
import collections
for year in range(2016, 2018):
for month in range(0, 13):
sauce = urllib.request.urlopen(Url1+str(month)+Url2+str(year)+Url3).read().decode('utf-8')
soup = bs(sauce, 'lxml')
select = soup.find_all('option', selected=True)
for i in select:
Month=select[4]
Year=select[3]
month=Month.text
year=Year.text
#print(year)
#print(month, year)
value = [x.text.strip() for x in soup.find_all("td", {"headers": regexV})]
country = [x.text.strip() for x in soup.find_all("a", {"href": regexC})]
quantity = [x.text.strip() for x in soup.find_all("td", {"headers": regexQ})]
total_list = [list(x) for x in zip(country,quantity,value)]
for item in total_list:
h=[year , month]
data = h + item
print(data)
df = pd.DataFrame(data=data)
df.head