I'm currently running the following code:
import requests
from bs4 import BeautifulSoup
from urlparse import urljoin
def hltv_match_list(max_offset):
offset = 0
while offset < max_offset:
url = 'http://www.hltv.org/?pageid=188&offset=' + str(offset)
base = "http://www.hltv.org/"
soup = BeautifulSoup(requests.get("http://www.hltv.org/?pageid=188&offset=0").content, 'html.parser')
cont = soup.select("div.covMainBoxContent a[href*=matchid=]")
href = urljoin(base, (a["href"] for a in cont))
# print([urljoin(base, a["href"]) for a in cont])
get_hltv_match_data(href)
offset += 50
def get_hltv_match_data(matchid_url):
source_code = requests.get(matchid_url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for teamid in soup.findAll("div.covSmallHeadline a[href*=teamid=]"):
print teamid.string
hltv_match_list(5)
Errors:
File "C:/Users/mdupo/PycharmProjects/HLTVCrawler/Crawler.py", line 12, in hltv_match_list
href = urljoin(base, (a["href"] for a in cont))
File "C:\Python27\lib\urlparse.py", line 261, in urljoin
urlparse(url, bscheme, allow_fragments)
File "C:\Python27\lib\urlparse.py", line 143, in urlparse
tuple = urlsplit(url, scheme, allow_fragments)
File "C:\Python27\lib\urlparse.py", line 182, in urlsplit
i = url.find(':')
AttributeError: 'generator' object has no attribute 'find'
Process finished with exit code 1
I think I'm having trouble with the href = urljoin(base, (a["href"] for a in cont)) part as I'm trying to create a url list I can feed into get_hltv_match_datato then capture various items within that page. Am I going about this wrong?
Cheers
You need to join each href as per your commented code:
urls = [urljoin(base,a["href"]) for a in cont]
You are trying to join the base url to a generator i.e (a["href"] for a in cont) which makes no sense.
You should also be passing the url to requests or you are going to be requesting the same page over and over.
soup = BeautifulSoup(requests.get(url).content, 'html.parser')
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 want to download after image crawling for multiple pages. However, all images cannot be downloaded because they are overwritten in [for syntax].
Below is my code. What is wrong?
from urllib.request import urlopen
from bs4 import BeautifulSoup
import requests as rq
for page in range(2,4):
baseUrl = 'https://onepiecetreasurecruise.fr/Artwork/index.php?page=index'
plusUrl = baseUrl + str(page)
html = urlopen(plusUrl).read()
soup = BeautifulSoup(html, 'html.parser')
img = soup.find_all(class_='card-img-top')
listimg = []
for i in img:
listimg.append(i['src'])
n = 1
for index, img_link in enumerate(listimg):
img_data = rq.get(img_link).content
with open('./onepiece/' + str(index+1) + '.png', 'wb+') as f:
f.write(img_data)
n += 1
Another way is to download all the pictures.
from simplified_scrapy import Spider, SimplifiedDoc, utils, SimplifiedMain
class ImageSpider(Spider):
name = 'onepiecetreasurecruise'
start_urls = ['https://onepiecetreasurecruise.fr/Artwork/index.php?page=index']
# refresh_urls = True
concurrencyPer1s = 0.5 # set download speed
imgPath = 'images/'
def __init__(self):
Spider.__init__(self, self.name) # necessary
utils.createDir(self.imgPath) # create image dir
def afterResponse(self, response, url, error=None, extra=None):
try: # save images
flag = utils.saveResponseAsFile(response, self.imgPath, 'image')
if flag: return None
except Exception as err:
print(err)
return Spider.afterResponse(self, response, url, error, extra)
def extract(self, url, html, models, modelNames):
doc = SimplifiedDoc(html)
# image urls
urls = doc.body.getElements('p', value='card-text').a
if (urls):
for u in urls:
u['header']={'Referer': url['url']}
self.saveUrl(urls)
# next page urls
u = doc.body.getElementByText('Suivant',tag='a')
if (u):
u['href'] = utils.absoluteUrl(url.url,u.href)
self.saveUrl(u)
return True
SimplifiedMain.startThread(ImageSpider()) # start download
I fixed the indents in your code. This works for me. It downloads 30 images.
from urllib.request import urlopen
from bs4 import BeautifulSoup
import requests as rq
listimg = [] # all images
for page in range(2,4):
baseUrl = 'https://onepiecetreasurecruise.fr/Artwork/index.php?page=index'
plusUrl = baseUrl + str(page)
html = urlopen(plusUrl).read()
soup = BeautifulSoup(html, 'html.parser')
img = soup.find_all(class_='card-img-top')
for i in img:
listimg.append(i['src'])
n = 1
for index, img_link in enumerate(listimg):
img_data = rq.get(img_link).content
with open('./onepiece/' + str(index+1) + '.png', 'wb+') as f:
f.write(img_data)
n += 1
#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 try to use scrapy xpath to scrape a page, but it seems it cannot capture the tag with predicates when I use a for loop,
# This package will contain the spiders of your Scrapy project
from cunyfirst.items import CunyfirstSectionItem
import scrapy
import json
class CunyfristsectionSpider(scrapy.Spider):
name = "cunyfirst-section-spider"
start_urls = ["file:///Users/haowang/Desktop/section.htm"]
def parse(self, response):
url = response.url
yield scrapy.Request(url, self.parse_page)
def parse_page(self, response):
n = -1
for section in response.xpath("//a[contains(#name,'MTG_CLASS_NBR')]"):
print(response.xpath("//a[#name ='MTG_CLASSNAME$10']/text()"))
n += 1
class_num = section.xpath('text()').extract_first()
# print(class_num)
classname = "MTG_CLASSNAME$" + str(n)
date = "MTG_DAYTIME$" + str(n)
instr = "MTG_INSTR$" + str(n)
print(classname)
class_name = response.xpath("//a[#name = classname]/text()")
I am looking for a tags with name as "MTG_CLASSNAME$" + str(n), with n being 0,1,2..., and I am getting empty output from my xpath query. Not sure why...
PS.
I am basically trying to scrape course and their info from https://hrsa.cunyfirst.cuny.edu/psc/cnyhcprd/GUEST/HRMS/c/COMMUNITY_ACCESS.CLASS_SEARCH.GBL?FolderPath=PORTAL_ROOT_OBJECT.HC_CLASS_SEARCH_GBL&IsFolder=false&IgnoreParamTempl=FolderPath%252cIsFolder&PortalActualURL=https%3a%2f%2fhrsa.cunyfirst.cuny.edu%2fpsc%2fcnyhcprd%2fGUEST%2fHRMS%2fc%2fCOMMUNITY_ACCESS.CLASS_SEARCH.GBL&PortalContentURL=https%3a%2f%2fhrsa.cunyfirst.cuny.edu%2fpsc%2fcnyhcprd%2fGUEST%2fHRMS%2fc%2fCOMMUNITY_ACCESS.CLASS_SEARCH.GBL&PortalContentProvider=HRMS&PortalCRefLabel=Class%20Search&PortalRegistryName=GUEST&PortalServletURI=https%3a%2f%2fhome.cunyfirst.cuny.edu%2fpsp%2fcnyepprd%2f&PortalURI=https%3a%2f%2fhome.cunyfirst.cuny.edu%2fpsc%2fcnyepprd%2f&PortalHostNode=ENTP&NoCrumbs=yes
with filter applied: Kingsborough CC, fall 18, BIO
Thanks!
Well... I've visited the website you put in the question description, I used element inspection and searched for "MTG_CLASSNAME" and I got 0 matches...
So I will give you some tools:
In your settings.py set that:
LOG_FILE = "log.txt"
LOG_STDOUT=True
then print the response body ( response.body ) where you should ( in the top of parse_page function in this case ) and search it in log.txt
Check there if there is what you are looking for.
If there is, use this https://www.freeformatter.com/xpath-tester.html (
or similar ) to check your xpath statement.
In addition, change for section in response.xpath("//a[contains(#name,'MTG_CLASS_NBR')]"):
by for section in response.xpath("//a[contains(#name,'MTG_CLASS_NBR')]").extract():, this will raise an error when you get the data that you are looking for.
I have a citation system which publishes users notes to a wiki (Researchr). Programmatically, I have access to the full BibTeX record of each entry, and I also display this on the individual pages (for example - click on BibTeX). This is in the interest of making it easy for users of other citation manager to automatically import the citation of a paper that interests them. I would also like other citation managers, especially Zotero, to be able to automatically detect and import a citation.
Zotero lists a number of ways of exposing metadata that it will understand, including meta tags with RDF, COiNS, Dublin Core and unAPI. Is there a Ruby library for converting BibTeX to any of these standards automatically - or a Javascript library? I could probably create something, but if something existed, it would be far more robust (BibTeX has so many publication types and fields etc).
There's a BibTeX2RDF convertor available here, might be what you're after.
unAPI is not a data standard - it's a way to serve data (to Zotero and other programs). Zotero imports Bibtex, so serving Bibtex via unAPI works just fine. Inspire is an example of a site that does that:
http://inspirehep.net/
By now one can simply import bibtex files of type .bib directly in Zotero. However, I noticed my bibtex files were often less complete than Zotero (in particular they often missed a DOI), and I did not find an "auto-complete" function (based on the data in the bibtex entries) in Zotero.
So I import the .bib file with Zotero, to ensure they are all in there. Then I run a python script that gets all the missing DOI's it can find for the entries in that .bib file, and exports them to a space separated .txt file.:
# pip install habanero
from habanero import Crossref
import re
def titletodoi(keyword):
cr = Crossref()
result = cr.works(query=keyword)
items = result["message"]["items"]
item_title = items[0]["title"]
tmp = ""
for it in item_title:
tmp += it
title = keyword.replace(" ", "").lower()
title = re.sub(r"\W", "", title)
# print('title: ' + title)
tmp = tmp.replace(" ", "").lower()
tmp = re.sub(r"\W", "", tmp)
# print('tmp: ' + tmp)
if title == tmp:
doi = items[0]["DOI"]
return doi
else:
return None
def get_dois(titles):
dois = []
for title in titles:
try:
doi = titletodoi(title)
print(f"doi={doi}, title={title}")
if not doi is None:
dois.append(doi)
except:
pass
# print("An exception occurred")
print(f"dois={dois}")
return dois
def read_titles_from_file(filepath):
with open(filepath) as f:
lines = f.read().splitlines()
split_lines = splits_lines(lines)
return split_lines
def splits_lines(lines):
split_lines = []
for line in lines:
new_lines = line.split(";")
for new_line in new_lines:
split_lines.append(new_line)
return split_lines
def write_dois_to_file(dois, filename, separation_char):
textfile = open(filename, "w")
for doi in dois:
textfile.write(doi + separation_char)
textfile.close()
filepath = "list_of_titles.txt"
titles = read_titles_from_file(filepath)
dois = get_dois(titles)
write_dois_to_file(dois, "dois_space.txt", " ")
write_dois_to_file(dois, "dois_per_line.txt", "\n")
The DOIs of the .txt are fed into magic wand of Zotero. Next, I (manually) remove the duplicates by choosing the latest added entry (because that comes from the magic wand with the most data).
After that, I run another script to update all the reference id's in my .tex and .bib files to those generated by Zotero:
# Importing library
import bibtexparser
from bibtexparser.bparser import BibTexParser
from bibtexparser.customization import *
import os, fnmatch
import Levenshtein as lev
# Let's define a function to customize our entries.
# It takes a record and return this record.
def customizations(record):
"""Use some functions delivered by the library
:param record: a record
:returns: -- customized record
"""
record = type(record)
record = author(record)
record = editor(record)
record = journal(record)
record = keyword(record)
record = link(record)
record = page_double_hyphen(record)
record = doi(record)
return record
def get_references(filepath):
with open(filepath) as bibtex_file:
parser = BibTexParser()
parser.customization = customizations
bib_database = bibtexparser.load(bibtex_file, parser=parser)
# print(bib_database.entries)
return bib_database
def get_reference_mapping(main_filepath, sub_filepath):
found_sub = []
found_main = []
main_into_sub = []
main_references = get_references(main_filepath)
sub_references = get_references(sub_filepath)
for main_entry in main_references.entries:
for sub_entry in sub_references.entries:
# Match the reference ID if 85% similair titles are detected
lev_ratio = lev.ratio(
remove_curly_braces(main_entry["title"]).lower(),
remove_curly_braces(sub_entry["title"]).lower(),
)
if lev_ratio > 0.85:
print(f"lev_ratio={lev_ratio}")
if main_entry["ID"] != sub_entry["ID"]:
print(f'replace: {sub_entry["ID"]} with: {main_entry["ID"]}')
main_into_sub.append([main_entry, sub_entry])
# Keep track of which entries have been found
found_sub.append(sub_entry)
found_main.append(main_entry)
return (
main_into_sub,
found_main,
found_sub,
main_references.entries,
sub_references.entries,
)
def remove_curly_braces(string):
left = string.replace("{", "")
right = left.replace("{", "")
return right
def replace_references(main_into_sub, directory):
for pair in main_into_sub:
main = pair[0]["ID"]
sub = pair[1]["ID"]
print(f"replace: {sub} with: {main}")
# UNCOMMENT IF YOU WANT TO ACTUALLY DO THE PRINTED REPLACEMENT
# findReplace(latex_root_dir, sub, main, "*.tex")
# findReplace(latex_root_dir, sub, main, "*.bib")
def findReplace(directory, find, replace, filePattern):
for path, dirs, files in os.walk(os.path.abspath(directory)):
for filename in fnmatch.filter(files, filePattern):
filepath = os.path.join(path, filename)
with open(filepath) as f:
s = f.read()
s = s.replace(find, replace)
with open(filepath, "w") as f:
f.write(s)
def list_missing(main_references, sub_references):
for sub in sub_references:
if not sub["ID"] in list(map(lambda x: x["ID"], main_references)):
print(f'the following reference has a changed title:{sub["ID"]}')
latex_root_dir = "some_path/"
main_filepath = f"{latex_root_dir}latex/Literature_study/zotero.bib"
sub_filepath = f"{latex_root_dir}latex/Literature_study/references.bib"
(
main_into_sub,
found_main,
found_sub,
main_references,
sub_references,
) = get_reference_mapping(main_filepath, sub_filepath)
replace_references(main_into_sub, latex_root_dir)
list_missing(main_references, sub_references)
# For those references which have levenshtein ratio below 85 you can specify a manual swap:
manual_swap = [] # main into sub
# manual_swap.append(["cantley_impact_2021","cantley2021impact"])
# manual_swap.append(["widemann_envision_2021","widemann2020envision"])
for pair in manual_swap:
main = pair[0]
sub = pair[1]
print(f"replace: {sub} with: {main}")
# UNCOMMENT IF YOU WANT TO ACTUALLY DO THE PRINTED REPLACEMENT
# findReplace(latex_root_dir, sub, main, "*.tex")
# findReplace(latex_root_dir, sub, main, "*.bib")