I have a list of urls and I am trying to scrape each of them to output in a single data frame. my code is below:
res=[]
for link in url_list:
html = urlopen(link)
soup = BeautifulSoup(html,'html.parser')
headers = [th.getText() for th in soup.findAll('tr', limit=2)[1].findAll('th')]
headers = headers[1:]
rows = soup.findAll('tr')[2:]
player_stats = [[td.getText() for td in rows[i].findAll('td')]
for i in range(len(rows))]
stats = pd.DataFrame(player_stats, columns = headers)
I only get output for one web page. Why is that?
You are overwriting your dataframe each time in your for loop. If you have a lot of pages, you can collect the individual dataframes and concatenate them.
df_hold_list = []
for link in url_list:
html = urlopen(link)
soup = BeautifulSoup(html,'html.parser')
headers = [th.getText() for th in soup.findAll('tr', limit=2)[1].findAll('th')]
headers = headers[1:]
rows = soup.findAll('tr')[2:]
player_stats = [[td.getText() for td in rows[i].findAll('td')]
for i in range(len(rows))]
df_hold_list.append(pd.DataFrame(player_stats, columns = headers))
stats = pd.concat(df_hold_list)
Related
I am trying to extract websites of the members from https://www.mhi.org/members. So, I wrote a code to visit the member page one by one and extract the web addresses. I am using BeautifulSoup Library to extract.
However my problem is not implementation of BeautifulSoup but in the for loop. The above link has 15 members per page. When I try to run the code for one page it just returns the web address of only one member. I have imported all the desired libraries.
url = input('Enter URL:')
#position = int(input('Enter position:'))-1
html = urlopen(url).read()
lst1 = list()
lst = list()
lst2 = list()
lst3 = list()
lst4 = list()
soup = BeautifulSoup(html,"html.parser")
url1 = "https://www.mhi.org"
conn = sqlite3.connect('list.sqlite')
cur = conn.cursor()
cur.execute('''CREATE TABLE IF NOT EXISTS weblinks (URL TEXT UNIQUE)''')
cur.execute('''CREATE TABLE IF NOT EXISTS weblinks1 (website TEXT UNIQUE)''')
cur.execute('''CREATE TABLE IF NOT EXISTS weblinks2 (website1 TEXT UNIQUE)''')
#print(soup)
for link in soup.find_all('a'):
lst.append(link.get('href'))
for links in lst:
if 'members' in links:
url2 = urllib.parse.urljoin(url1, links)
lst2.append(url2)
#print(lst2)
url3 = lst2[4:18]
print(url3)
for x in url3:
html1 = urlopen(x).read()
soup1 = BeautifulSoup(html1,"html.parser")
for url4 in soup1.find_all('a'):
url4 = url4.get('href')
if url4 not in lst3:
lst3.append(url4)
url6 = lst3.pop(108)
print(url6)
So, the last "for loop" where url6 is the desired output. It just prints output one web address.
Please advise what am I missing here.
#i have scraped data below is my code, now i want to add a column of symbols to the respective company data, plz guide me how the symbol can be added to the respective firm data
#code below
from time import sleep
import pandas as pd
import os
import numpy as np
from bs4 import BeautifulSoup
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
browser = webdriver.Chrome(ChromeDriverManager().install())
symbols =['FATIMA',
'SSGC',
'FCCL',
'ISL',
'KEL',
'NCL',
'DGKC',
'SNGP',
'NML',
'ENGRO',
'HUMNL',
'CHCC',
'ATRL',
'HUBC',
'ASTL',
'PIBTL',
'OGDC',
'EFERT',
'FFC',
'NCPL',
'KTML',
'PSO',
'LUCK',
'SEARL',
'KOHC',
'ABOT',
'AICL',
'HASCOL',
'PTC',
'KAPCO',
'PIOC',
'POL',
'SHEL',
'GHGL',
'HCAR',
'DCR',
'BWCL',
'MTL',
'GLAXO',
'PKGS',
'SHFA','MARI',
'ICI',
'ACPL',
'PSMC',
'SPWL',
'THALL',
'BNWM',
'EFUG',
'GADT',
'AABS']
company = 1
for ThisSymbol in symbols :
# Get first symbol from the above python list
company = 2
# In the URL, make symbol as variable
url = 'http://www.scstrade.com/stockscreening/SS_CompanySnapShotYF.aspx?symbol=' + ThisSymbol
browser.get(url)
sleep(2)
# The below command will get all the contents from the url
html = browser.execute_script("return document.documentElement.outerHTML")
# So we will supply the contents to beautiful soup and we tell to consider this text as a html, with the following command
soup = BeautifulSoup (html, "html.parser")
for rn in range(0,9) :
plist = []
r = soup.find_all('tr')[rn]
# Condition: if first row, then th, otherwise td
if (rn==0) :
celltag = 'th'
else :
celltag = 'td'
# Now use the celltag instead of using fixed td or th
col = r.find_all(celltag)
print()
if col[i] == 0:
print ("")
else:
for i in range(0,4) :
cell = col[i].text
clean = cell.replace('\xa0 ', '')
clean = clean.replace (' ', '')
plist.append(clean)
# If first row, create df, otherwise add to it
if (rn == 0) :
df = pd.DataFrame(plist)
else :
df2 = pd.DataFrame(plist)
colname = 'y' + str(2019-rn)
df[colname] = df2
if (company == 1):
dft = df.T
# Get header Column
head = dft.iloc[0]
# Exclude first row from the data
dft = dft[1:]
dft.columns = head
dft = dft.reset_index()
# Assign Headers
dft = dft.drop(['index'], axis = 'columns')
else:
dft2 = df.T
# Get header Column
head = dft2.iloc[0]
# Exclude first row from the data
dft2 = dft2[1:]
dft2.columns = head
dft2 = dft2.reset_index()
# Assign Headers
dft2 = dft2.drop(['index'], axis = 'columns')
dft['Symbol'] = ThisSymbol
dft = dft.append(dft2, sort=['Year','Symbol'])
company = company +1
dft
my output looks this, i want to have a symbol column to each respective firm data
Symbol,i have added
dft['Symbol'] = ThisSymbol
but it add just first company from the list to all companies data
enter image description here
I am trying to extract chapter titles and their subtitles from a web page in the url. This is my spider
import scrapy
from ..items import ContentsPageSFBItem
class BasicSpider(scrapy.Spider):
name = "contentspage_sfb"
#allowed_domains = ["web"]
start_urls = [
'https://www.safaribooksonline.com/library/view/shell-programming-in/9780134496696/',
]
def parse(self, response):
item = ContentsPageSFBItem()
item['content_item'] = response.xpath('normalize-space(//ol[#class="detail-toc"]//*/text())').extract();
length = len(response.xpath('//ol[#class="detail-toc"]//*/text()').extract()); #extract()
full_url_list = list();
title_list = list();
for i in range(1,length+1):
full_url_list.append(response.url)
item["full_url"] = full_url_list
title = response.xpath('//title[1]/text()').extract();
for j in range(1,length+1):
title_list.append(title)
item["title"] = title_list
return item
Even though I use the normalise fucntion in my xpath to remove the spaces, I get the following result in my csv
content_item,full_url,title
"
,Chapter 1,
,
,
,Instructor Introduction,
,00:01:00,
,
,
,Course Overview,
How do I get the result with at most only one new line after each entry?
If you want to get all text within Table of Contents section you need to change your xpath expression in item['content_item'] to:
item['content_item'] = response.xpath('//ol[#class="detail-toc"]//a/text()').extract()
You can rewrite you spider code like this:
import scrapy
class BasicSpider(scrapy.Spider):
name = "contentspage_sfb"
start_urls = [
'https://www.safaribooksonline.com/library/view/shell-programming-in/9780134496696/',
]
def parse(self, response):
item = dict() # change dict to your scrapy item
for link in response.xpath('//ol[#class="detail-toc"]//a'):
item['link_text'] = link.xpath('text()').extract_first()
item['link_url'] = response.urljoin(link.xpath('#href').extract_first())
yield item
# Output:
{'link_text': 'About This E-Book', 'link_url': 'https://www.safaribooksonline.com/library/view/shell-programming-in/9780134496696/pref00.html#pref00'}
{'link_text': 'Title Page', 'link_url': 'https://www.safaribooksonline.com/library/view/shell-programming-in/9780134496696/title.html#title'}
I am trying to crawl a website. I want to do it for different dates. So i am storing date in a list. But while trying to access items of list, crawler works only for 1st value in list. Please help. following is my code:
class SpidyQuotesViewStateSpider(scrapy.Spider):
name = 'retail_price'
def start_requests(self):
print "start request"
urls = "http://fcainfoweb.nic.in/PMSver2/Reports/Report_Menu_web.aspx"
yield scrapy.Request(url=urls, callback=self.parse)
def parse(self, response):
dated = ["05/03/2017","04/03/2017"]
urls = "http://fcainfoweb.nic.in/PMSver2/Reports/Report_Menu_web.aspx"
#frmdata =
cookies1 ={}
val = response.headers.getlist('Set-Cookie')
print "login session values" ,response.headers.getlist('Set-Cookie')
if(len(val) != 0):
cookies1['ASP.NET_SessionId'] = str(response.headers.getlist('Set-Cookie')[0].split(";")[0].split("=")[1])
cookies1['path'] = str(response.headers.getlist('Set-Cookie')[0].split(";")[1].split("=")[1])
print cookies1;
for i in range(len(dated)):
yield scrapy.FormRequest(url=urls, callback=self.parse1, formdata={'ctl00$MainContent$btn_getdata1':"Get Data",
'ctl00$MainContent$Txt_FrmDate':dated[i],
'ctl00$MainContent$Ddl_Rpt_Option0':"Daily Prices",
'ctl00$MainContent$Rbl_Rpt_type':"Price report",
'ctl00$MainContent$ddl_Language':"English",
'ctl00$MainContent$Ddl_Rpt_type':"Retail",
'__EVENTVALIDATION':"IwZyKgfTXVzxiHxiPXGk/W8XQZBDb0EOPxJh6s8hofq0ffqOpiHSH77CafcxySF3PbkYgSMNFCJhLM2cGnL6SxT0PJuGDCJtV0V8Y4a94UErUCiSANiin+4uKckk9v9Ux8JqTVeaipppmlH+wyks2U9SgPfkNUsqw4eHCkDyB5akNNZImRIixOHHVY3JSXGkwXn7ueK9w+AgnqJzpXaWdMr9J1++M4VAFImSNF8brFSfPHe5kb/qzkGIwUr/KRouaRYK8WLWZh/Mbl9xwREwhDSxWJSOdihSE0WWoaqSMtpaR99rDDCsD3mdJqfu0aPIlREupTZRzlrmztXU0eS3949YW+ywdTRvykaMNgOW2Q4saYP5j/niKbRW6GiDnaLV2A38X/HW80+trrsjwJr9tjTKVFyikf6s/3gzyiTp11ivSkwIY2b3hutjYn7OfTDo",
#'__EVENTVALIDATION':"HqVo2xHk04clYwnBposXbZGhbIr181A7RbyeZv74Cia7rXSKmpOpbeSnn3XXnoDJKRxMK0W9nxKZFfkNje+P/K7gE5HVjHJr9Gr0Gs46TntzKDsvzyii8jZ7e0fdZgQCJKoXxQNgR2vNkWqChKcEldBuMHCOgJRqCNCF/JPFKpdKZoIWr7GU8rhzwLijf/Gkm+FuTULs/fl2HHK6Z1QQEozzEHFsDwzl0G4IiN//eNYfHuUBXKZ3wdZzPqG0s53WHEuSBzhqBC9AtCJOs4ZZhdtwFh8iyTJ4PlsLP9DLHYHRCOAd72UO0UH8gT7gAkKVo1I4L540DilowOR9SttH7MM/oOs9qhKlnG61FgqkYGW8zGzF/yNEXO+beVAK1RVvuO+FDnuq/g36TRnUieei5GpAZ+96CSoCIxykdvHx8R+smTNF/5erlowV4ci+tcI7",
'__VIEWSTATEENCRYPTED':"",
'__VIEWSTATEGENERATOR':"85862B00",
'__VIEWSTATE':"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",
#'__VIEWSTATE':"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",
'__LASTFOCUS':"",
'__EVENTARGUMENT':"",
'__EVENTTARGET':"",
'ctl00_MainContent_ToolkitScriptManager1_HiddenField':";;AjaxControlToolkit,+Version=4.1.51116.0,+Culture=neutral,+PublicKeyToken=28f01b0e84b6d53e:en-US:fd384f95-1b49-47cf-9b47-2fa2a921a36a:475a4ef5:addc6819:5546a2b:d2e10b12:effe2a26:37e2e5c9:5a682656:c7029a2:e9e598a9"},method='POST',cookies = cookies1)
def parse1(self, response):
path1 = "id('Panel1')"
value1 = response.xpath(path1).extract_first()
print value1
First of all, you are sending the spider more time on the same site, though with different form parameters. You have therefore to use dont_filter=True in the request, otherwise Scrapy blocks duplicate calls.
Then it seems to me that the site you are scraping don't allow you to make more than one request during the same session. Try for example to go to http://fcainfoweb.nic.in/PMSver2/Reports/Report_Menu_web.aspx with your browser, compile the form, get the data and than to go back to the initial page: It's impossible. So you have to modify your spider. Here's a very rough code just to give an idea. It works for me, but please don't use it in production!
class SpidyQuotesViewStateSpider(scrapy.Spider):
name = 'retail_price'
urls = "http://fcainfoweb.nic.in/PMSver2/Reports/Report_Menu_web.aspx"
def start_requests(self):
dated = ["01/03/2017","05/03/2017","04/03/2017"]
for i in dated:
request = scrapy.Request(url=self.urls, dont_filter=True, callback=self.parse)
request.meta['question'] = i
yield request
def parse(self, response):
thedate = response.meta['question']
cookies1 ={}
val = response.headers.getlist('Set-Cookie')
print("login session values" ,response.headers.getlist('Set-Cookie'))
if(len(val) != 0):
cookies1['ASP.NET_SessionId'] = str(str(response.headers.getlist('Set-Cookie')[0]).split(";")[0].split("=")[1])
cookies1['path'] = str(str(response.headers.getlist('Set-Cookie')[0]).split(";")[1].split("=")[1])
yield scrapy.FormRequest(url=self.urls, dont_filter=True, callback=self.parse1, formdata={'ctl00$MainContent$btn_getdata1':"Get Data",
'ctl00$MainContent$Txt_FrmDate': thedate,
'ctl00$MainContent$Ddl_Rpt_Option0':"Daily Prices",
'ctl00$MainContent$Rbl_Rpt_type':"Price report",
'ctl00$MainContent$ddl_Language':"English",
'ctl00$MainContent$Ddl_Rpt_type':"Retail",
'__EVENTVALIDATION':"IwZyKgfTXVzxiHxiPXGk/W8XQZBDb0EOPxJh6s8hofq0ffqOpiHSH77CafcxySF3PbkYgSMNFCJhLM2cGnL6SxT0PJuGDCJtV0V8Y4a94UErUCiSANiin+4uKckk9v9Ux8JqTVeaipppmlH+wyks2U9SgPfkNUsqw4eHCkDyB5akNNZImRIixOHHVY3JSXGkwXn7ueK9w+AgnqJzpXaWdMr9J1++M4VAFImSNF8brFSfPHe5kb/qzkGIwUr/KRouaRYK8WLWZh/Mbl9xwREwhDSxWJSOdihSE0WWoaqSMtpaR99rDDCsD3mdJqfu0aPIlREupTZRzlrmztXU0eS3949YW+ywdTRvykaMNgOW2Q4saYP5j/niKbRW6GiDnaLV2A38X/HW80+trrsjwJr9tjTKVFyikf6s/3gzyiTp11ivSkwIY2b3hutjYn7OfTDo",
#'__EVENTVALIDATION':"HqVo2xHk04clYwnBposXbZGhbIr181A7RbyeZv74Cia7rXSKmpOpbeSnn3XXnoDJKRxMK0W9nxKZFfkNje+P/K7gE5HVjHJr9Gr0Gs46TntzKDsvzyii8jZ7e0fdZgQCJKoXxQNgR2vNkWqChKcEldBuMHCOgJRqCNCF/JPFKpdKZoIWr7GU8rhzwLijf/Gkm+FuTULs/fl2HHK6Z1QQEozzEHFsDwzl0G4IiN//eNYfHuUBXKZ3wdZzPqG0s53WHEuSBzhqBC9AtCJOs4ZZhdtwFh8iyTJ4PlsLP9DLHYHRCOAd72UO0UH8gT7gAkKVo1I4L540DilowOR9SttH7MM/oOs9qhKlnG61FgqkYGW8zGzF/yNEXO+beVAK1RVvuO+FDnuq/g36TRnUieei5GpAZ+96CSoCIxykdvHx8R+smTNF/5erlowV4ci+tcI7",
'__VIEWSTATEENCRYPTED':"",
'__VIEWSTATEGENERATOR':"85862B00",
'__VIEWSTATE':"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",
#'__VIEWSTATE':"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",
'__LASTFOCUS':"",
'__EVENTARGUMENT':"",
'__EVENTTARGET':"",
'ctl00_MainContent_ToolkitScriptManager1_HiddenField':";;AjaxControlToolkit,+Version=4.1.51116.0,+Culture=neutral,+PublicKeyToken=28f01b0e84b6d53e:en-US:fd384f95-1b49-47cf-9b47-2fa2a921a36a:475a4ef5:addc6819:5546a2b:d2e10b12:effe2a26:37e2e5c9:5a682656:c7029a2:e9e598a9"},method='POST',cookies = cookies1)
def parse1(self, response):
path1 = "id('Panel1')"
value1 = response.xpath(path1).extract_first()[:574]
print(value1)
I am trying to download images from multiple urls from a search in google images.
However, i only want 15 images from each url.
class imageSpider(BaseSpider):
name = "image"
start_urls = [
'https://google.com/search?q=simpsons&tbm=isch'
'https://google.com/search?q=futurama&tbm=isch'
]
def parse(self,response):
hxs = HtmlXPathSelector(response)
items = []
images = hxs.select("//div[#id='ires']//div//a[#href]")
count = 0
for image in images:
count += 1
item = ImageItem()
image_url = image.select(".//img[#src]")[0].extract()
import urlparse
image_absolute_url = urlparse.urljoin(response.url, image_url.strip())
index = image_absolute_url.index("src")
changedUrl = image_absolute_url[index+5:len(image_absolute_url)-2]
item['image_urls'] = [changedUrl]
index1 = site['url'].index("search?q=")
index2 = site['url'].index("&tbm=isch")
imageName = site['url'][index1+9:index2]
download(changedUrl,imageName + str(count)+".png")
items.append(item)
if count == 15:
break
return items
The download function downloads the images (i have code for that. that's not the problem).
The problem is that when i break, it stops at the first url and never continues on to the next url. How could i make it download 15 images for the first url and then 15 images for the 2nd url. I am using break because there are about 1000 images in every google images page and i don't want that many.
The problem is not about break statement. you have missed a comma in start_urls.
it should be like this:
start_urls = [
'http://google.com/search?q=simpsons&tbm=isch',
'http://google.com/search?q=futurama&tbm=isch'
]