Created
August 1, 2019 00:00
-
-
Save itsJlot/e4edc8f68aa98903b0ba3371400209b0 to your computer and use it in GitHub Desktop.
Wikipedia scraper with Neo4J Graph
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests, bs4 as bs, time as t,re,matplotlib.pyplot as plot,py2neo as neo | |
graph = nx.Graph() | |
neograph = neo.Graph("bolt://localhost:7687",auth=("neo4j","neo4jpass")) | |
matcher = neo.NodeMatcher(neograph) | |
randomNode = matcher.match("Article", name="Random").first() | |
if not randomNode: | |
randomNode = neo.Node("Article", name="Random") | |
neograph.create(randomNode) | |
def getBSoupFromLink(link): | |
return bs.BeautifulSoup(requests.get(link).text,"html.parser") | |
for x in range(50): | |
curLink = "/wiki/Special:Random" | |
startingTitle = "Random" | |
startingNode = randomNode | |
for x in range(300): | |
#print(type(curLink)) | |
startingLink = curLink | |
bsoup = getBSoupFromLink("https://en.wikipedia.org"+curLink) | |
heading = bsoup.find("h1",attrs={"id":"firstHeading"}).text | |
tables = bsoup.find_all("table") | |
if len(tables) > 0: | |
infotable = tables | |
for table in infotable: | |
table.decompose() | |
thumbs = bsoup.find_all("div",class_=True) | |
if len(thumbs) > 0: | |
thumb = thumbs[0] | |
thumb.decompose() | |
mwpo = bsoup.find("div",attrs={"class":"mw-parser-output"}) | |
if mwpo: | |
links = mwpo.find_all("a",href=re.compile("^/w[^:#]*$"))#,class_=["mw-redirect",False]) | |
else: | |
break | |
for link in links: | |
if not ("anguage" in link["href"] or bool(re.search("[#?]",link["href"]))): | |
#print(link["href"], " does not contain #? or Language", ("anguage" in link["href"]), bool(re.search("[#?]",link["href"]))) | |
if not link.parent.has_attr("role") and not link.parent.has_attr("class") and not link.parent.name == u"i": | |
curLink = link["href"] | |
break | |
print(startingTitle,"->",heading, "\n", curLink, "\n", "-" * 50) | |
currentNodeList = matcher.match("Article", name=heading).limit(1) | |
if len(currentNodeList) > 0: | |
currentNode = currentNodeList.first() | |
neograph.create(neo.Relationship(startingNode, "LinksTo", currentNode)) | |
break | |
else: | |
currentNode = neo.Node("Article",name=heading) | |
neograph.create(currentNode) | |
print(startingNode,currentNode) | |
neograph.create(neo.Relationship(startingNode,"LinksTo",currentNode)) | |
startingTitle = heading | |
startingNode = currentNode | |
#nx.draw_networkx(graph,font_size = 5,nodesize=50) | |
#plot.show() | |
#nx.node_link_data() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment